Search results for: language learning model

Authors: Christiane Dumont

Abstract:

This paper proposes to revisit foreign-language learning as a tool to increase motivation through advocacy and develop effective natural communication skills, which are critical leadership qualities. To this end, collaborative initiatives undertaken by advanced university students of French with local and international community partners will be reviewed. Close attention will be paid to the acquisition of intercultural skills, the reflective process, as well as the challenges and outcomes. Two international development projects conducted in Haiti will be highlighted, i.e., collaboration with a network of providers in the Haitian cultural heritage preservation and tourism sector (2014-15) and development of investigation and teacher training tools for a primary/secondary school in the Port-au-Prince area (current). The choice of community-service learning as a framework to teach French-as-a-second-language stemmed from the need to raise awareness against stereotypes and prejudice, which hinder the development of effective intercultural skills. This type of experiential education also proved very effective in identifying and preventing miscommunication caused by the lack of face-to-face interaction in our increasingly technology-mediated world. Learners experienced first-hand, the challenges and advantages of face-to-face communication, which, in turn, enhanced their motivation for developing effective intercultural skills. Vygotsky's and Kolb's theories, current research on service learning (Dwight, Eyler), action/project-based pedagogy (Beckett), and reflective learning (TSC Farrell), will provide useful background to analyze the benefits and challenges of community-service learning. The ultimate goal of this paper is to find out what makes experiential learning truly unique and transformative for both the learners and the community they wish to serve. It will demonstrate how enhanced motivation, community engagement, and clear, concise, and respectful communication impact and empower learners. The underlying hope is to help students in high-profile, and leading-edge industries become effective global leaders.

Keywords: experiential learning, intercultural communication, reflective learning, effective leadership, learner motivation

Procedia PDF Downloads 101

Authors: Lana Whiskeyjack, Kyle Napier

Abstract:

The Spirit of the language embodies the motivation for indigenous people to connect with the indigenous language of their lineage. While the concept of the spirit of the language is often woven into the discussion by indigenous language revitalizationists, particularly those who are indigenous, there are few tangible terms in academic research conceptually actualizing the term. Through collaborative work with indigenous language speakers, elders, and learners, this research sets out to identify the spirit of the language, the catalysts of disconnection from the spirit of the language, and the sources of reconnection to the spirit of the language. This work fundamentally addresses the terms of engagement around collaboration with indigenous communities, itself inviting a decolonial approach to community outreach and individual relationships. As indigenous researchers, this means beginning, maintain, and closing this work in the ceremony while being transparent with community members in this work and related publishing throughout the project’s duration. Decolonizing this approach also requires maintaining explicit ongoing consent by the elders, knowledge keepers, and community members when handling their ancestral and indigenous knowledge. The handling of this knowledge is regarded in this work as stewardship, both in the handling of digital materials and the handling of ancestral Indigenous knowledge. This work observes recorded conversations in both nêhiyawêwin and English, resulting from 10 semi-structured interviews with fluent nêhiyawêwin speakers as well as three structured dialogue circles with fluent and emerging speakers. The words were transcribed by a speaker fluent in both nêhiyawêwin and English. The results of those interviews were categorized thematically to conceptually actualize the spirit of the language, catalysts of disconnection to thespirit of the language, and community voices methods of reconnection to the spirit of the language. Results of these interviews vastly determine that the spirit of the language is drawn from the land. Although nêhiyawêwin is the focus of this work, Indigenous languages are by nature inherently related to the land. This is further reaffirmed by the Indigenous language learners and speakers who expressed having ancestries and lineages from multiple Indigenous communities. Several other key differences embody this spirit of the language, which include ceremony and spirituality, as well as the semantic worldviews tied to polysynthetic verb-oriented morphophonemics most often found in indigenous languages — and of focus, nêhiyawêwin. The catalysts of disconnection to the spirit of the language are those whose histories have severed connections between Indigenous Peoples and the spirit of their languages or those that have affected relationships with the land, ceremony, and ways of thinking. Results of this research and its literature review have determined the three most ubiquitously damaging interdependent factors, which are catalysts of disconnection from the spirit of the language as colonization, capitalism, and Christianity. As voiced by the Indigenous language learners, this work necessitates addressing means to reconnect to the spirit of the language. Interviewees mentioned that the process of reconnection involves a whole relationship with the land, the practice of reciprocal-relational methodologies for language learning, and indigenous-protected and -governed learning. This work concludes in support of those reconnection methodologies.

Keywords: indigenous language acquisition, indigenous language reclamation, indigenous language revitalization, nêhiyawêwin, spirit of the language

Procedia PDF Downloads 135

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health-related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores to text, ranging from positive, neutral, and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing and tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial, and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced, and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process and substituting the Naive Bayes for a deep learning neural network model.

Keywords: sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model

Procedia PDF Downloads 87

Authors: Zahra Mirsanjari, Mohammad Reza Baradaran, Mehdi Rastegari Ghiri

Abstract:

Research in the field of education has widely documented that teachers’ sense of efficacy has strong impacts on various aspects of teaching and learning. The present study is an attempt to examine Iranian EFL teachers’ degree of self-efficacy for teaching English. The data required for the study was gathered from Iranian EFL teachers teaching English as a foreign language in different schools and language institutes in Iran. Data were collected using Teacher’s Sense of Efficacy Scale (TSES). Results identified four dimensions of teachers’ English teaching-specific sense of efficacy: instructional strategies, classroom management, student engagement, and oral English language use. It was also found that teachers rated their self-efficacy in teaching English at a moderate level in the dimensions of instructional strategies, classroom management, and student engagement. Results have implications for language teachers and practitioners.

Keywords: Self-efficacy, teaching, EFL, teachers

Procedia PDF Downloads 519

Authors: Heny Hartono, Cecilia Titiek Murniati

Abstract:

The pandemic has given teachers and students no other choice but having full online learning. In such an emergency situation as the time of the covid-19 pandemic, the application of LMS (Learner Management System) in higher education is the most reasonable solution for students and teachers. In fact, the online learning requires all elements of a higher education systems, including the human resources, infrastructure, and supporting systems such as the application, server, and stable internet connection. The readiness of the higher education institution in preparing the online system may secure those who are involved in the online learning process. It may also result in students’ self-efficacy in online learning. This research aimed to investigate how students perceive their self-efficacy in online English learning, especially in speaking classes which is considered as a productive language skill. This research collects qualitative data with narrative inquiry involving 25 students of speaking classes as the respondents. The results of this study show that students perceive their self-efficacy in speaking online classes as not very high.

Keywords: self-efficacy, online learning, speaking class, college students, e-learning

Procedia PDF Downloads 92

Authors: Clifford Irikefe Gbeyonron

Abstract:

Applied linguists concur that there is low-level achievement in English language use among Nigerian secondary school students. One of the factors that exacerbate this is classroom feature of which large class size is obvious. This study investigated the impact of large classes on learning English as a second language (ESL) at junior secondary school (JSS) in Yobe State. To achieve this, Solomon four-group experimental design was used. 382 subjects were divided into four groups and taught ESL for thirteen weeks. 356 subjects wrote the post-test. Data from the systematic observation and post-test were analyzed via chi square and ANOVA. Results indicated that learners in large classes (LLC) attain lower linguistic progress than learners in small classes (LSC). Furthermore, LSC have more chances to access teacher evaluation and participate actively in classroom discourse than LLC. In consequence, large classes have adverse effects on learning ESL in Yobe State. This is inimical to English language education given that each learner of ESL has their individual peculiarity within each class. It is recommended that strategies that prioritize individualization, grouping, use of language teaching aides, and theorization of innovative models in respect of large classes be considered.

Keywords: large classes, achievement, classroom discourse

Procedia PDF Downloads 400

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 114

Authors: Baladitya Swaika, Rahul Khatry

Abstract:

Computer Adaptive Tests (CATs) is one of the most efficient ways for testing the cognitive abilities of students. CATs are based on Item Response Theory (IRT) which is based on item selection and ability estimation using statistical methods of maximum information selection/selection from posterior and maximum-likelihood (ML)/maximum a posteriori (MAP) estimators respectively. This study aims at combining both classical and Bayesian approaches to IRT to create a dataset which is then fed to a neural network which automates the process of ability estimation and then comparing it to traditional CAT models designed using IRT. This study uses python as the base coding language, pymc for statistical modelling of the IRT and scikit-learn for neural network implementations. On creation of the model and on comparison, it is found that the Neural Network based model performs 7-10% worse than the IRT model for score estimations. Although performing poorly, compared to the IRT model, the neural network model can be beneficially used in back-ends for reducing time complexity as the IRT model would have to re-calculate the ability every-time it gets a request whereas the prediction from a neural network could be done in a single step for an existing trained Regressor. This study also proposes a new kind of framework whereby the neural network model could be used to incorporate feature sets, other than the normal IRT feature set and use a neural network’s capacity of learning unknown functions to give rise to better CAT models. Categorical features like test type, etc. could be learnt and incorporated in IRT functions with the help of techniques like logistic regression and can be used to learn functions and expressed as models which may not be trivial to be expressed via equations. This kind of a framework, when implemented would be highly advantageous in psychometrics and cognitive assessments. This study gives a brief overview as to how neural networks can be used in adaptive testing, not only by reducing time-complexity but also by being able to incorporate newer and better datasets which would eventually lead to higher quality testing.

Keywords: computer adaptive tests, item response theory, machine learning, neural networks

Procedia PDF Downloads 167

Authors: Mst. Tuhin Akter, Sharun Akter Khushbu, S. M. Shaqib

Abstract:

A real-time system architecture is highly effective for monitoring and detecting various damaged products or fruits that may deteriorate over time or become infected with diseases. Deep learning models have proven to be effective in building such architectures. However, building a deep learning model from scratch is a time-consuming and costly process. A more efficient solution is to utilize deep neural network (DNN) based transfer learning models in the real-time monitoring architecture. This study focuses on using a novel strawberry dataset to develop effective transfer learning models for the proposed real-time monitoring system architecture, specifically for evaluating and detecting strawberry freshness. Several state-of-the-art transfer learning models were employed, and the best performing model was found to be Xception, demonstrating higher performance across evaluation metrics such as accuracy, recall, precision, and F1-score.

Keywords: strawberry freshness evaluation, deep neural network, transfer learning, image augmentation

Procedia PDF Downloads 74

Authors: Lai Wenfang

Abstract:

Tthis study will describe how to use artificial intelligence (AI) technology to build the user-oriented platform for integrated archival service. The platform will be launched in 2020 by the National Archives Administration (NAA) in Taiwan. With the progression of information communication technology (ICT) the NAA has built many systems to provide archival service. In order to cope with new challenges, such as new ICT, artificial intelligence or blockchain etc. the NAA will try to use the natural language processing (NLP) and machine learning (ML) skill to build a training model and propose suggestions based on the data sent to the platform. NAA expects the platform not only can automatically inform the sending agencies’ staffs which records catalogues are against the transfer or destroy rules, but also can use the model to find the details hidden in the catalogues and suggest NAA’s staff whether the records should be or not to be, to shorten the auditing time. The platform keeps all the users’ browse trails; so that the platform can predict what kinds of archives user could be interested and recommend the search terms by visualization, moreover, inform them the new coming archives. In addition, according to the Archives Act, the NAA’s staff must spend a lot of time to mark or remove the personal data, classified data, etc. before archives provided. To upgrade the archives access service process, the platform will use some text recognition pattern to black out automatically, the staff only need to adjust the error and upload the correct one, when the platform has learned the accuracy will be getting higher. In short, the purpose of the platform is to deduct the government digital transformation and implement the vision of a service-oriented smart government.

Keywords: artificial intelligence, natural language processing, machine learning, visualization

Procedia PDF Downloads 163

Authors: Senol Dogan, Gunay Karli

Abstract:

Identification of relevant publications based on a Medline query is time-consuming and error-prone. An all based process has the potential to solve this problem without any manual work. To the best of our knowledge, our study is the first to investigate the ability of machine learning to identify relevant articles accurately. 5 different machine learning algorithms were tested using 23 predictors based on several metadata fields attached to publications. We find that the Boosted model is the best-performing algorithm and its overall accuracy is 96%. In addition, specificity and sensitivity of the algorithm is 97 and 93%, respectively. As a result of the work, we understood that we can apply the same procedure to understand cancer gene expression big data.

Keywords: prediction of publications, machine learning, algorithms, bariatric surgery, comparison of algorithms, boosted, tree, logistic regression, ANN model

Procedia PDF Downloads 199

Authors: Luz Janeth Ospina M.

Abstract:

The fourth industrial revolution is changing the role of education substantially and, therefore, the role of instructors and learners at all levels. Education 4.0 is an imminent response to the needs of a globalized world where humans and technology are being aligned to enable endless possibilities, among them the need for students, as digital natives, to communicate effectively in at least one language besides their mother tongue, and also the requirement of developing theirs. This is an exploratory study in which a control group (N = 21), all of the students of Spanish as a foreign language at the university level, after taking a Spanish class, responded to an online questionnaire about the engagement, atmosphere, and environment in which their course was delivered. These aspects considered in the survey were relative to the instructor’s teaching style, including: (a) active, hands-on learning; (b) flexibility for in-class activities, easily switching between small group work, individual work, and whole-class discussion; and (c) integrating technology into the classroom. Strongly believing in these principles, the instructor deliberately taught the course in a SCALE-UP room, as it could facilitate such a positive and encouraging learning environment. These aspects are trends related to Education 4.0 and have become integral to the instructor’s pedagogical stance that calls for a constructive-affective role, instead of a transmissive one. As expected, with a learning environment that (a) fosters student engagement and (b) improves student outcomes, the subjects were highly engaged, which was partially due to the learning environment. An overwhelming majority (all but one) of students agreed or strongly agreed that the atmosphere and the environment were ideal. Outcomes of this study are relevant and indicate that it is about time for teachers to build up a meaningful correlation between humans and technology. We should see the trends of Education 4.0 not as a threat but as practices that should be in the hands of critical and creative instructors whose pedagogical stance responds to the needs of the learners in the 21st century.

Keywords: active learning, education 4.0, higher education, pedagogical stance

Procedia PDF Downloads 110

Authors: Elena Pozdnyakova

Abstract:

“Government Relations” is a field of knowledge presently taught at the majority of universities around the globe. English as the default language can become the language of teaching since the issues discussed are both global and national in character. However for this field of knowledge key concepts and their word representations in English don’t often coincide with those in other languages. International master’s degree students abroad as well as students, taught the course in English at their national universities, are exposed to difficulties, connected with correct conceptualizing of terminology of GR in British and American academic traditions. The study was carried out during the GR English language course elaboration (pilot research: 2013 -2015) at Moscow State Institute of Foreign Relations (University), Russian Federation. Within this period, English language instructors designed and elaborated the three-semester course of GR. Methodologically the course design was based on elaboration model with the special focus on conceptual elaboration sequence and theoretical elaboration sequence. The course designers faced difficulties in concept selection and theoretical elaboration sequence. To improve the results and eliminate the problems with concept selection, a new, corpus-based approach was worked out. The computer-based tool WordSmith 6.0 was used with the aim to build a model of key concept selection. The corpus of GR English texts consisted of 1 million words (the study corpus). The approach was based on measuring effect size, i.e. the percent difference of the frequency of a word in the study corpus when compared to that in the reference corpus. The results obtained proved significant improvement in the process of concept selection. The corpus-based model also facilitated theoretical elaboration of teaching materials.

Keywords: corpus-based study, English as the default language, key concepts, measuring effect size, model of key concept selection

Procedia PDF Downloads 295

Authors: Shafaq Rubab

Abstract:

One of the biggest reasons of dropouts from schools is lack of motivation and interest among the students, particularly in mathematics. Many developing countries are facing this problem and this issue is lowering the literacy rate in these developing countries. The best solution for increasing motivation level and interest among the students is using tablet game-based learning. However, a pedagogically sound game required a well-planned instructional design model to enhance learner’s attention and confidence otherwise effectiveness of the learning games suffers badly. This research aims to evaluate the impact of the pedagogically sound instructional design model on students’ motivation by using tablet game-based learning. This research was conducted among the out-of-school-students having an age range from 7 to 12 years and the sample size of two hundred students was purposively selected without any gender discrimination. Qualitative research was conducted by using a survey tool named Instructional Material Motivational Survey (IMMS) adapted from Keller Arcs model. A comparison of results from both groups’ i.e. experimental group and control group revealed that motivation level of the students taught by the game was higher than the students instructed by using conventional methodologies. Experimental group’s students were more attentive, confident and satisfied as compared to the control group’s students. This research work not only promoted the trend of digital game-based learning in developing countries but also supported that a pedagogically sound instructional design model utilized in an educational game can increase the motivation level of the students and can make the learning process a totally immersive and interactive fun loving activity.

Keywords: digital game-based learning, student’s motivation, instructional design model, learning process

Procedia PDF Downloads 417

Authors: Kira Gulko Morse

Abstract:

Choosing one’s primary language may not be as common as choosing an additional foreign language to study or use during travel. In some instances, however, it becomes a matter of internal personal struggle, as language is tied not only to specific circumstances but also to human background and identity. This phenomenological qualitative study focuses on the factors affecting the decision of a person to undergo a language shift. Specifically, it considers how these factors relate to identity negotiation and expression. The data for the study include the analysis of published autobiographical narratives and personal interviews conducted using the Responsive Interviewing model. While research participants come from a variety of geographical locations and have used different reasons for undergoing their individual language shift, the study identifies a number of common features shared by all the participants. Specifically, while all the participants have been able to maintain their first language to varying degrees of proficiency, they have all completed the shift to establish a primary language different from their first. Additionally, the process of self-identification is found to be directly connected to the phenomenon of language choice for each of the participants. The findings of the study further tie the phenomenon of individual language shift to a more comprehensive issue of individual life choices – ethnic revival, immigration, and inter-cultural marriage among others. The study discusses varying language roles and the data indicate that language shift may occur whether it is a symbolic driving force or a secondary means in fulfilling a set life goal. The concept of language addition is suggested as an alternative to the arbitrariness of language shift. Thus, instead of focusing on subtractive bilingualism or language loss, the emphasis becomes the integration of languages within the individual. The study emphasizes the importance of the construct of personal choice in its connection to individual language shift. It places the focus from society onto an individual and the ability of an individual to make decisions in matters of linguistic identification.

Keywords: choice theory, identity negotiation, language shift, psycholinguistics

Procedia PDF Downloads 127

Authors: Suriya

Abstract:

Rapid socio-economic development and urbanization have led to an increasingly serious air pollution problem in Ulaanbaatar (UB), the capital of Mongolia. PM₂.₅ pollution has become the most pressing aspect of UB air pollution. Therefore, monitoring and predicting PM₂.₅ concentration in UB is of great significance for the health of the local people and environmental management. As of yet, very few studies have used models to predict PM₂.₅ concentrations in UB. Using data from 0:00 on June 1, 2018, to 23:00 on April 30, 2020, we proposed two deep learning models based on Bayesian-optimized LSTM (Bayes-LSTM) and CNN-LSTM. We utilized hourly observed data, including Himawari8 (H8) aerosol optical depth (AOD), meteorology, and PM₂.₅ concentration, as input for the prediction of PM₂.₅ concentrations. The correlation strengths between meteorology, AOD, and PM₂.₅ were analyzed using the gray correlation analysis method; the comparison of the performance improvement of the model by using the AOD input value was tested, and the performance of these models was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The prediction accuracies of Bayes-LSTM and CNN-LSTM deep learning models were both improved when AOD was included as an input parameter. Improvement of the prediction accuracy of the CNN-LSTM model was particularly enhanced in the non-heating season; in the heating season, the prediction accuracy of the Bayes-LSTM model slightly improved, while the prediction accuracy of the CNN-LSTM model slightly decreased. We propose two novel deep learning models for PM₂.₅ concentration prediction in UB, Bayes-LSTM, and CNN-LSTM deep learning models. Pioneering the use of AOD data from H8 and demonstrating the inclusion of AOD input data improves the performance of our two proposed deep learning models.

Keywords: deep learning, AOD, PM2.5, prediction, Ulaanbaatar

Procedia PDF Downloads 40

Authors: Kai Zhu, Shanhua He, Yujiao Chang

Abstract:

This paper explores the virtual linguistic landscape of an emerging virtual language community in TikTok, a language community realizing immediate and non-immediate communication without a precise Spatio-temporal domain or a specific socio-cultural boundary or interpersonal network. This kind of language community generates a large number and various forms of virtual linguistic landscape, with which we conducted a virtual ethnographic survey together with telephone interviews to collect data from coping. We have been following two language communities in TikTok for several months so that we can illustrate the composition of the two language communities and some typical virtual language landscapes in both language communities first. Then we try to explore the reasons why and how they are formed through the organization, transcription, and analysis of the interviews. Our analysis reveals the richness and diversity of the virtual linguistic landscape, and finally, we summarize some of the characteristics of this language community.

Keywords: virtual linguistic landscape, virtual language community, virtual ethnographic survey, TikTok

Procedia PDF Downloads 95

Authors: Hsin Lee, Hsuan Lee

Abstract:

Legal artificial intelligence (LegalAI) has been increasing applications within legal systems, propelled by advancements in natural language processing (NLP). Compared with general documents, legal case documents are typically long text sequences with intrinsic logical structures. Most existing language models have difficulty understanding the long-distance dependencies between different structures. Another unique challenge is that while the Judiciary of Taiwan has released legal judgments from various levels of courts over the years, there remains a significant obstacle in the lack of labeled datasets. This deficiency makes it difficult to train models with strong generalization capabilities, as well as accurately evaluate model performance. To date, models in Taiwan have yet to be specifically trained on judgment data. Given these challenges, this research proposes a Longformer-based pre-trained language model explicitly devised for retrieving similar judgments in Taiwanese legal documents. This model is trained on a self-constructed dataset, which this research has independently labeled to measure judgment similarities, thereby addressing a void left by the lack of an existing labeled dataset for Taiwanese judgments. This research adopts strategies such as early stopping and gradient clipping to prevent overfitting and manage gradient explosion, respectively, thereby enhancing the model's performance. The model in this research is evaluated using both the dataset and the Average Entropy of Offense-charged Clustering (AEOC) metric, which utilizes the notion of similar case scenarios within the same type of legal cases. Our experimental results illustrate our model's significant advancements in handling similarity comparisons within extensive legal judgments. By enabling more efficient retrieval and analysis of legal case documents, our model holds the potential to facilitate legal research, aid legal decision-making, and contribute to the further development of LegalAI in Taiwan.

Keywords: legal artificial intelligence, computation and language, language model, Taiwanese legal cases

Procedia PDF Downloads 64

Authors: Kaustubh Chakradeo, Michael Delves, Sofya Titarenko

Abstract:

Malaria is a serious disease which affects hundreds of millions of people around the world, each year. If not treated in time, it can be fatal. Despite recent developments in malaria diagnostics, the microscopy method to detect malaria remains the most common. Unfortunately, the accuracy of microscopic diagnostics is dependent on the skill of the microscopist and limits the throughput of malaria diagnosis. With the development of Artificial Intelligence tools and Deep Learning techniques in particular, it is possible to lower the cost, while achieving an overall higher accuracy. In this paper, we present a VGG-based model and compare it with previously developed models for identifying infected cells. Our model surpasses most previously developed models in a range of the accuracy metrics. The model has an advantage of being constructed from a relatively small number of layers. This reduces the computer resources and computational time. Moreover, we test our model on two types of datasets and argue that the currently developed deep-learning-based methods cannot efficiently distinguish between infected and contaminated cells. A more precise study of suspicious regions is required.

Keywords: convolution neural network, deep learning, malaria, thin blood smears

Procedia PDF Downloads 122

Authors: Soni Ariawan

Abstract:

The discourse of language and culture relation is an interesting issue to be researched. The debate is not about what comes first, language or culture, but it strongly argues that learning foreign language also means learning the culture of the language. The more interesting issue found once constructing an EFL textbook dealing with proportional representation among source culture, target culture and international culture. This study investigates cultural content representation in EFL textbook grade 10 year 2017 in Indonesia. Cortazzi and Jin’s theoretical framework is employed to analyse the reading texts, conversations, and images. The finding shows that national character as the main agenda of Indonesian government is revealed in this textbook since the textbook more frequently highlights the source culture (Indonesian culture) compared to target and international culture. This is aligned with the aim of Indonesian government to strengthen the national identity and promoting local culture awareness through education. To conclude, the study is expected to be significant in providing the idea for government to consider cultural balances representation in constructing textbook. Furthermore, teachers and students should be aware of cultural content revealed in the EFL textbook and be able to enhance intercultural communication not only in the classroom but also in a wider society.

Keywords: EFL textbook, intercultural communication, local culture, target culture, international culture

Procedia PDF Downloads 214

Authors: Nabil Shawkat, Jamil Saquer

Abstract:

Social media has accelerated our ability to engage with others and eliminated many communication barriers. On the other hand, the widespread use of social media resulted in an increase in online hate speech. This has drastic impacts on vulnerable individuals and societies. Therefore, it is critical to detect hate speech to prevent innocent users and vulnerable communities from becoming victims of hate speech. We investigate the performance of different deep learning and machine learning algorithms on three different datasets. Our results show that the BERT model gives the best performance among all the models by achieving an F1-score of 90.6% on one of the datasets and F1-scores of 89.7% and 88.2% on the other two datasets.

Keywords: hate speech, machine learning, deep learning, abusive words, social media, text classification

Procedia PDF Downloads 123

Authors: Lee Bih Ni

Abstract:

This paper discusses that good learning involves all academic groups in the school. Blended learning is learning outside the classroom. Google Classroom is a free service learning app for schools, non-profit organizations and anyone with a personal Google account. Facilities accessed through computers and mobile phones are very useful for school teachers and students. Blended learning classrooms using both traditional and technology-based methods for teaching have become the norm for many educators. Using Google Classroom gives students access to online learning. Even if the teacher is not in the classroom, the teacher can provide learning. This is the supervision of the form of the teacher when the student is outside the school.

Keywords: blended learning, learning app, google classroom, schools

Procedia PDF Downloads 137

Authors: Roberto Feltrero, Sara Osuna-Acedo

Abstract:

Responsible Research and Innovation have to accomplish one fundamental aim: everybody has to participate in the benefits of innovation, but also innovation has to be democratic; that is to say, everybody may have the possibility to participate in the decisions in the innovation process. Particularly, a democratic and inclusive model of social participation and innovation includes persons with disabilities and people at risk of discrimination. Innovations on Artificial Intelligence for social development have to accomplish the same dual goal: improving equality for accessing fields of public interest like education, training and public services, as well as improving civic and democratic participation in the process of developing such innovations for all. This research aims to develop innovations, policies and policy recommendations to apply and disseminate such artificial intelligence and social model for making educational and administrative processes more accessible. First, designing a citizen participation process to engage citizens in the designing and use of artificial intelligence tools for public services. This will result in improving trust in democratic institutions contributing to enhancing the transparency, effectiveness, accountability and legitimacy of public policy-making and allowing people to participate in the development of ethical standards for the use of such technologies. Second, improving educational tools for lifelong learning with AI models to improve accountability and educational data management. Dissemination, education and social participation will be integrated, measured and evaluated in innovative educational processes to make accessible all the educational technologies and content developed on AI about responsible and social innovation. A particular case will be presented regarding access for all to educational tools and public services. This accessibility requires cognitive adaptability because, many times, legal or administrative language is very complex. Not only for people with cognitive disabilities but also for old people or citizens at risk of educational or social discrimination. Artificial Intelligence natural language processing technologies can provide tools to translate legal, administrative, or educational texts to a more simple language that can be accessible to everybody. Despite technological advances in language processing and machine learning, this becomes a huge project if we really want to respect ethical and legal consequences because that kinds of consequences can only be achieved with civil and democratic engagement in two realms: 1) to democratically select texts that need and can be translated and 2) to involved citizens, experts and nonexperts, to produce and validate real examples of legal texts with cognitive adaptations to feed artificial intelligence algorithms for learning how to translate those texts to a more simple and accessible language, adapted to any kind of population.

Keywords: responsible research and innovation, AI social innovations, cognitive accessibility, public participation

Procedia PDF Downloads 81

Authors: Fakieh Alrabai

Abstract:

This study investigated the effects on learner anxiety of anxiety-reducing strategies utilized by English as foreign language teachers in Saudi Arabia. The study was conducted in two stages. In the first stage, sources of foreign language anxiety for Saudi learners of English (N = 596) were identified using The Foreign Language Classroom Anxiety Scale (FLCAS). In the second stage, 465 learners who were divided almost equally into two groups (experimental vs. control) and 12 teachers were recruited. Anxiety-reducing strategies were implemented exclusively in the treatment group for approximately eight weeks. FLCAS was used to assess learners’ FL anxiety levels before and after treatment. Statistical analyses (e.g. ANOVA and ANCOVA) were used to evaluate the study findings. These findings revealed that the intervention led to significantly decreased levels of FL anxiety for learners in the experimental group compared with increased levels of anxiety for those in the control group.

Keywords: communication apprehension, EFL teaching/learning, fear of negative evaluation, foreign language anxiety

Procedia PDF Downloads 342

Authors: Asra Yousuf, Ajaykumar Tannirkulum

Abstract:

Inferring rural-urban migration trends can help design effective policies that promote better urban planning and rural development. In this paper, we describe how machine learning algorithms can be applied to predict internal migration decisions of people. We consider data collected from household surveys in Tamil Nadu to train our model. To measure the performance of the model, we use data on past migration from National Sample Survey Organisation of India. The factors for training the model include socioeconomic characteristic of each individual like age, gender, place of residence, outstanding loans, strength of the household, etc. and his past migration history. We perform a comparative analysis of the performance of a number of machine learning algorithm to determine their prediction accuracy. Our results show that machine learning algorithms provide a stronger prediction accuracy as compared to statistical models. Our goal through this research is to propose the use of data science techniques in understanding human decisions and behaviour in developing countries.

Keywords: development, migration, internal migration, machine learning, prediction

Procedia PDF Downloads 259

Authors: Jennifer Leach, Umashanger Thayasivam

Abstract:

The use of technology has benefited society in more ways than one ever thought possible. Unfortunately, though, as society’s knowledge of technology has advanced, so has its knowledge of ways to use technology to manipulate people. This has led to a simultaneous advancement in the world of fraud. Machine learning techniques can offer a possible solution to help decrease this advancement. This research explores how the use of various machine learning techniques can aid in detecting fraudulent activity across two different types of fraudulent data, and the accuracy, precision, recall, and F1 were recorded for each method. Each machine learning model was also tested across five different training and testing splits in order to discover which testing split and technique would lead to the most optimal results.

Keywords: data science, fraud detection, machine learning, supervised learning

Procedia PDF Downloads 180

Authors: Elham Sharifineyestani, Mohammad Farshchin

Abstract:

Tropical cyclones are one of the most expensive and deadliest natural disasters. They cause heavy rainfall and serious flash flooding that result in billions of dollars of damage and considerable mortality each year in the United States. Prediction of the frequency of tropical cyclone-induced rainfall events can be helpful in emergency planning and flood risk management. In this study, we have developed a machine-learning model to predict the exceedance frequencies of tropical cyclone-induced rainfall events in the United States. Model results show a satisfactory agreement with available observations. To examine the effectiveness of our approach, we also have compared the result of our predictions with the exceedance frequencies predicted using a physics-based rainfall model by Feldmann.

Keywords: flash flooding, tropical cyclones, frequencies, machine learning, risk management

Procedia PDF Downloads 236

Authors: Qing Wu, Fei-Yan Li, Heng-Chang Zhang

Abstract:

Multitask learning support vector machines (SVMs) have recently attracted increasing research attention. Given several related tasks, the single-task learning methods trains each task separately and ignore the inner cross-relationship among tasks. However, multitask learning can capture the correlation information among tasks and achieve better performance by training all tasks simultaneously. In addition, the asymmetric squared loss function can better improve the generalization ability of the models on the most asymmetric distributed data. In this paper, we first make two assumptions on the relatedness among tasks and propose two multitask learning proximal support vector machine algorithms, named MTL-a-PSVM and EMTL-a-PSVM, respectively. MTL-a-PSVM seeks a trade-off between the maximum expectile distance for each task model and the closeness of each task model to the general model. As an extension of the MTL-a-PSVM, EMTL-a-PSVM can select appropriate kernel functions for shared information and private information. Besides, two corresponding special cases named MTL-PSVM and EMTLPSVM are proposed by analyzing the asymmetric squared loss function, which can be easily implemented by solving linear systems. Experimental analysis of three classification datasets demonstrates the effectiveness and superiority of our proposed multitask learning algorithms.

Keywords: multitask learning, asymmetric squared loss, EMTL-a-PSVM, classification

Procedia PDF Downloads 101

Authors: Fatin Mansour Daas

Abstract:

Language education responds to and is reflective of emerging social and political trends. Language policies and practices are shaped by political, economic, social and cultural considerations. Following this, Israeli language education policy as implemented in Arab schools in Israel is influenced by the particular political and social situation of Arab-Palestinian citizens of Israel. This national group remained in their homeland following the war in 1948 between Israel and its Arab neighbors and became Israeli citizens following the establishment of the State of Israel. This study examines language policy in Arab schools in Israel from 1948 until the present time in light of the unique experience of the Palestinian Arab homeland minority in Israel with a particular focus on questions of politics and identity. The establishment of the State of Israel triggered far-reaching political, social and educational transformations within Arab Palestinian society in Israel, including in the area of language and language studies. Since 1948, the linguistic repertoire of Palestinian Arabs in Israel has become more complex and diverse, while the place and status of different languages have changed. Following the establishment of the State of Israel, only Hebrew and Arabic were retained as the official languages, and Israeli policy reflected this in schools as well: with the advent of the Jewish state, Hebrew language education among Palestinians in Israel has increased. Similarly, in Arab Palestinian schools in Israel, English is taught as a third language, Hebrew as a second language, and Arabic as a first language – even though it has become less important to native Arabic speakers. This research focuses on language studies and language policy in the Arab school system in Israel from 1948 onwards. It will analyze the relative focus of language education between the different languages, the rationale of various language education policies, and the pedagogic approach used to teach each language and student achievements vis-à-vis language skills. This study seeks to understand the extent to which Arab schools in Israel are multi-lingual by examining successes, challenges and difficulties in acquiring the respective languages. This qualitative study will analyze five different components of language education policy: (1) curriculum, (2) learning materials; (3) assessment; (4) interviews and (5) archives. Firstly, it consists of an analysis examining language education curricula, learning materials and assessments used in Arab schools in Israel from 1948-2018 including a selection of language textbooks for the compulsory years of study and the final matriculation (Bagrut) examinations. The findings will also be based on archival material which traces the evolution of language education policy in Arabic schools in Israel from the years 1948-2018. This archival research, furthermore, will reveal power relations and general decision-making in the field of the Arabic education system in Israel. The research will also include interviews with Ministry of Education staff who provide instructional oversight in the instruction of the three languages in the Arabic education system in Israel. These interviews will shed light on the goals of language education as understood by those who are in charge of implementing policy.

Keywords: language education policy, languages, multilingualism, language education, educational policy, identity, Palestinian-Arabs, Arabs in Israel, educational school system

Procedia PDF Downloads 84

Authors: Francesca Perri

Abstract:

This paper describes a proposal for a teachers’ training course, focused on the introduction of corpora in the EFL didactics (English as a foreign language) of some Italian secondary schools. The training course is conceived as a part of a TEDD participant’s five months internship. TEDD (Technologies for Education: diversity and devices) is an advanced course held by the Department of Engineering and Information Technology at the University of Trento, Italy. Its main aim is to train a selected, heterogeneous group of graduates to engage with the complex interdependence between education and technology in modern society. The educational approach draws on a plural coexistence of various theories as well as socio-constructivism, constructionism, project-based learning and connectivism. TEDD educational model stands as the main reference source to the design of a formative course for EFL teachers, drawing on the digitalization of didactics and creation of learning interactive materials for L2 intermediate students. The training course lasts ten hours, organized into five sessions. In the first part (first and second session) a series of guided and semi-guided activities drive participants to familiarize with corpora through the use of a digital tools kit. Then, during the second part, participants are specifically involved in the realization of a ML (Mistakes Laboratory) where they create, develop and share digital activities according to their teaching goals with the use of corpora, supported by the digital facilitator. The training course takes place into an ICT laboratory where the teachers work either individually or in pairs, with a computer connected to a wi-fi connection, while the digital facilitator shares inputs, materials and digital assistance simultaneously on a whiteboard and on a digital platform where participants interact and work together both synchronically and diachronically. The adoption of good ICT practices is a fundamental step to promote the introduction and use of Corpus Linguistics in EFL teaching and learning processes, in fact dealing with corpora not only promotes L2 learners’ critical thinking and orienteering versus wild browsing when they are looking for ready-made translations or language usage samples, but it also entails becoming confident with digital tools and activities. The paper will explain reasons, limits and resources of the pedagogical approach adopted to engage EFL teachers with the use of corpora in their didactics through the promotion of digital practices.

Keywords: digital didactics, education, language learning, teacher training

Procedia PDF Downloads 142