Search results for: unsupervised sentiment analysis

Authors: Hanan M. Alghamdi, Kholud E. Alsalami, Manal I. Alshaikhi, Nouf M. Alsalami, Sara A. Awad, Ruqaya A. Alrabei

Abstract:

Tourism in Saudi Arabia is one of the emerging sectors with rapid growth. The Kingdom of Saudi Arabia is characterized by its wonderful and historical areas, which constitute important cultural and tourist landmarks. These landmarks attract the attention of the government of Saudi Arabia; hence the improvement of the tourism sector becomes one of the important axes of Saudi Arabia's vision 2030. There is a need to enhance the tourist experience by facilitating the tourism process for visitors to the Kingdom of Saudi Arabia. This project aims to design an application to serve domestic tourists and visitors from outside the Kingdom of Saudi Arabia. This application will contain an automated tourist generate plan service by sentiment analysis of comments in Google Map using Lexicon for method Rule-based approach. There are thirteen regions in the kingdom of Saudi Arabia. The regions supported in this application will be Makkah and Asir regions. According to the output of the sentiment analysis, the application will recommend restaurants and cafes, activities (parks, museums) and shopping (shopping centers) in the generated plan. After that, the system will show the user a drop-down list of “Mega-events in Saudi Arabia” containing a link to the site of events in the Kingdom of Saudi Arabia. and “important information for you” public decency regulations.

Keywords: tourist automated plan, sentiment analysis, comments in google map, tourism in Saudi Arabia

Procedia PDF Downloads 108

Authors: Yaxin Bi, Peter Nicholl

Abstract:

The rapid advancement of Information and communication technologies (ICT) is extremely influencing every aspect of Higher Education. It has transformed traditional teaching, learning, assessment and feedback into a new era of Digital Education. This also introduces many challenges in capturing and understanding student engagement with their studies in Higher Education. The School of Computing at Ulster University has developed a Feedback And Notification (FAN) Online tool that has been used to send students links to personalized feedback on their submitted assessments and record students’ frequency of review of the shared feedback as well as the speed of collection. The feedback that the students initially receive is via a personal email directing them through to the feedback via a URL link that maps to the feedback created by the academic marker. This feedback is typically a Word or PDF report including comments and the final mark for the work submitted approximately three weeks before. When the student clicks on the link, the student’s personal feedback is viewable in the browser and they can view the contents. The FAN tool provides the academic marker with a report that includes when and how often a student viewed the feedback via the link. This paper presents an investigation into student engagement through analyzing the interaction timestamps and frequency of review by the student. We have proposed an approach to modeling interaction timestamps and use sentiment classification techniques to analyze the data collected over the last five years for a set of modules. The data studied is across a number of final years and second-year modules in the School of Computing. The paper presents the details of quantitative analysis methods and describes further their interactions with the feedback overtime on each module studied. We have projected the students into different groups of engagement based on sentiment analysis results and then provide a suggestion of early targeted intervention for the set of students seen to be under-performing via our proposed model.

Keywords: feedback, engagement, interaction modelling, sentiment analysis

Procedia PDF Downloads 71

Authors: Francesca Radice

Abstract:

Domestic and sexual violence provokes, on average in Australia, one female death per week due to intimate violence behaviours. 83% of couples meet online, and intercepting domestic and sexual violence at this level would be beneficial. It has been observed that violent or coercive behaviour has been apparent from initial conversations on dating apps like Tinder. Child pornography, stalking, and coercive control are some criminal offences from dating apps, including women murdered after finding partners through Tinder. Police databases and predictive policing are novel approaches taken to prevent crime before harm is done. This research will investigate how police databases can be used in a privacy-preserving way to characterise users in terms of their potential for violent crime. Using the COPS database of NSW Police, we will explore how the past criminal record can be interpreted to yield a category of potential danger for each dating app user. It is up to the judgement of each subscriber on what degree of the potential danger they are prepared to enter into. Sentiment analysis is an area where research into natural language processing has made great progress over the last decade. This research will investigate how sentiment analysis can be used to interpret interchanges between dating app users to detect manipulative or coercive sentiments. These can be used to alert law enforcement if continued for a defined number of communications. One of the potential problems of this approach is the potential prejudice a categorisation can cause. Another drawback is the possibility of misinterpreting communications and involving law enforcement without reason. The approach will be thoroughly tested with cross-checks by human readers who verify both the level of danger predicted by the interpretation of the criminal record and the sentiment detected from personal messages. Even if only a few violent crimes can be prevented, the approach will have a tangible value for real people.

Keywords: sentiment analysis, data mining, predictive policing, virtual manipulation

Procedia PDF Downloads 54

Authors: Melissa Vang, Raheyma Khan, Haihua Chen

Abstract:

The coronavirus disease 2019 (COVID‐19) pandemic has changed people's lives from all over the world. More people have turned to Twitter to engage online and discuss the COVID-19 vaccine. This study aims to present a text mining approach to identify people's attitudes towards the COVID-19 vaccine on Twitter. To achieve this purpose, we collected 54,268 COVID-19 vaccine tweets from September 01, 2020, to November 01, 2020, then the BERT model is used for the sentiment and topic analysis. The results show that people had more negative than positive attitudes about the vaccine, and countries with an increasing number of confirmed cases had a higher percentage of negative attitudes. Additionally, the topics discussed in positive and negative tweets are different. The tweet datasets can be helpful to information professionals to inform the public about vaccine-related informational resources. Our findings may have implications for understanding people's cognitions and feelings about the vaccine.

Keywords: BERT, COVID-19 vaccine, sentiment analysis, topic modeling

Procedia PDF Downloads 118

Authors: Marcelino Caetano Noronha, Vosco Pereira, Jose Soares Pinto, Ferdinando Da C. Saores

Abstract:

One particularly popular social media platform is Youtube. It’s a video-sharing platform where users can submit videos, and other users can like, dislike or comment on the videos. In this study, we conduct a binary classification task on YouTube’s video comments and review from the users regarding the accession process of Timor Leste to become the eleventh member of the Association of South East Asian Nations (ASEAN). We scrape the data directly from the public YouTube video and apply several pre-processing and weighting techniques. Before conducting the classification, we categorized the data into two classes, namely positive and negative. In the classification part, we apply Support Vector Machine (SVM) algorithm. By comparing with Naïve Bayes Algorithm, the experiment showed SVM achieved 84.1% of Accuracy, 94.5% of Precision, and Recall 73.8% simultaneously.

Keywords: classification, YouTube, sentiment analysis, support sector machine

Procedia PDF Downloads 67

Authors: Kamal Amarouche, Houda Benbrahim, Ismail Kassou

Abstract:

Nowadays, e-commerce shopping websites have experienced noticeable growth. These websites have gained consumers’ trust. After purchasing a product, many consumers share comments where opinions are usually embedded about the given product. Research on the automatic management of opinions that gives suggestions to potential consumers and portrays an image of the product to manufactures has been growing recently. After launching the product in the market, the reviews generated around it do not usually contain helpful information or generic opinions about this product (e.g. telephone: great phone...); in the sense that the product is still in the launching phase in the market. Within time, the product becomes old. Therefore, consumers perceive the advantages/ disadvantages about each specific product feature. Therefore, they will generate comments that contain their sentiments about these features. In this paper, we present an unsupervised method to extract different product features hidden in the opinions which influence its purchase, and that combines Time Weighting (TW) which depends on the time opinions were expressed with Term Frequency-Inverse Document Frequency (TF-IDF). We conduct several experiments using two different datasets about cell phones and hotels. The results show the effectiveness of our automatic feature extraction, as well as its domain independent characteristic.

Keywords: opinion mining, product feature extraction, sentiment analysis, SentiWordNet

Procedia PDF Downloads 366

Authors: Colette Malyack, Pius Egbelu

Abstract:

Business-to-Customer (B2C) delivery options have improved to meet increased demand in recent years. The change in end users has forced logistics networks to focus on customer service and sentiment that would have previously been the priority of the company or organization of origin. This has led to increased pressure on logistics companies to extend traditional B2B networks into a B2C solution while accommodating additional costs, roadblocks, and customer sentiment; the result has been the creation of the omnichannel delivery network encompassing a number of traditional and modern methods of package delivery. In this paper the many solutions within the omnichannel delivery network are defined and discussed. It can be seen through this analysis that the omnichannel delivery network can be applied to reduce the complexity of package delivery and provide customers with more options. Applied correctly the result is a reduction in cost to the logistics company over time, even with an initial increase in cost to obtain the technology.

Keywords: network planning, last mile delivery, omnichannel delivery network, omnichannel logistics

Procedia PDF Downloads 116

Authors: Tian Zhang

Abstract:

Unsupervised object segmentation aims at segmenting objects in sequential images and obtaining the mask of each object without any manual intervention. Unsupervised segmentation remains a challenging task due to the lack of prior knowledge about these objects. Previous methods often require manually specifying the action of each object, which is often difficult to obtain. Instead, this paper does not need action information of objects and automatically learns the actions and relations among objects from the structured environment. To obtain the object segmentation of sequential images, the relationships between objects and images are extracted to infer the action and interaction of objects based on the multi-head attention mechanism. Three types of objects’ relationships in the object segmentation task are proposed: the relationship between objects in the same frame, the relationship between objects in two frames, and the relationship between objects and historical information. Based on these relationships, the proposed model (1) is effective in multiple objects segmentation tasks, (2) just needs images as input, and (3) produces better segmentation results as more relationships are considered. The experimental results on multiple datasets show that this paper’s method achieves state-of-art performance. The quantitative and qualitative analyses of the result are conducted. The proposed method could be easily extended to other similar applications.

Keywords: unsupervised object segmentation, attention mechanism, contrastive learning, structured environment

Procedia PDF Downloads 84

Authors: Zelalem Fantahun

Abstract:

Part-of-speech tagging is the process of assigning a part-of-speech or other lexical class marker to each word into naturally occurring text. Part-of-speech tagging is the most fundamental and basic task almost in all natural language processing. In natural language processing, the problem of providing large amount of manually annotated data is a knowledge acquisition bottleneck. Since, Amharic is one of under-resourced language, the availability of tagged corpus is the bottleneck problem for natural language processing especially for POS tagging. A promising direction to tackle this problem is to provide a system that does not require manually tagged data. In unsupervised learning, the learner is not provided with classifications. Unsupervised algorithms seek out similarity between pieces of data in order to determine whether they can be characterized as forming a group. This paper explicates the development of unsupervised part-of-speech tagger using K-Means clustering for Amharic language since large amount of data is produced in day-to-day activities. In the development of the tagger, the following procedures are followed. First, the unlabeled data (raw text) is divided into 10 folds and tokenization phase takes place; at this level, the raw text is chunked at sentence level and then into words. The second phase is feature extraction which includes word frequency, syntactic and morphological features of a word. The third phase is clustering. Among different clustering algorithms, K-means is selected and implemented in this study that brings group of similar words together. The fourth phase is mapping, which deals with looking at each cluster carefully and the most common tag is assigned to a group. This study finds out two features that are capable of distinguishing one part-of-speech from others these are morphological feature and positional information and show that it is possible to use unsupervised learning for Amharic POS tagging. In order to increase performance of the unsupervised part-of-speech tagger, there is a need to incorporate other features that are not included in this study, such as semantic related information. Finally, based on experimental result, the performance of the system achieves a maximum of 81% accuracy.

Keywords: POS tagging, Amharic, unsupervised learning, k-means

Procedia PDF Downloads 414

Authors: Yahya Almurtadha, Mukhtar Ghaleb, Ahmed M. Shamsan Saleh

Abstract:

The world witnessed a fierce attack from the Covid-19 virus, which affected public life socially, economically, healthily and psychologically. The world's governments tried to confront the pandemic by imposing a number of precautionary measures such as general closure, curfews and social distancing. Scientists have also made strenuous efforts to develop an effective vaccine to train the immune system to develop antibodies to combat the virus, thus reducing its symptoms and limiting its spread. Artificial intelligence, along with researchers and medical authorities, has accelerated the vaccine development process through big data processing and simulation. On the other hand, one of the most important negatives of the impact of Covid 19 was the state of anxiety and fear due to the blowout of rumors through social media, which prompted governments to try to reassure the public with the available means. This study aims to proposed using Sentiment Analysis (AKA Opinion Mining) and deep learning as efficient artificial intelligence techniques to work on retrieving the tweets of the public from Twitter and then analyze it automatically to extract their opinions, expression and feelings, negatively or positively, about the symptoms they may feel after vaccination. Sentiment analysis is characterized by its ability to access what the public post in social media within a record time and at a lower cost than traditional means such as questionnaires and interviews, not to mention the accuracy of the information as it comes from what the public expresses voluntarily.

Keywords: deep learning, opinion mining, natural language processing, sentiment analysis

Procedia PDF Downloads 143

Authors: Elisa Santana-Monagas, Juan L. Núñez, Jaime León, Samuel Falcón, Celia Fernández, Rocío P. Solís

Abstract:

Teaching practices have been widely studied in relation to students' outcomes, positioning themselves as one of their strongest catalysts and influencing students' emotional experiences. In the higher education context, teachers become even more crucial as many students ground their decisions on which courses to enroll in based on opinions and ratings of teachers from other students. Unfortunately, sometimes universities do not provide the personal, social, and academic stimulation students demand to be actively engaged. To evaluate their teachers, universities often rely on students' evaluations of teaching (SET) collected via Likert scale surveys. Despite its usefulness, such a method has been questioned in terms of validity and reliability. Alternatively, researchers can rely on qualitative answers to open-ended questions. However, the unstructured nature of the answers and a large amount of information obtained requires an overwhelming amount of work. The present work presents an alternative approach to analyse such data: sentiment analysis. To the best of our knowledge, no research before has included results from SA into an explanatory model to test how students' sentiments affect their emotional engagement in class. The sample of the present study included a total of 225 university students (Mean age = 26.16, SD = 7.4, 78.7 % women) from the Educational Sciences faculty of a public university in Spain. Data collection took place during the academic year 2021-2022. Students accessed an online questionnaire using a QR code. They were asked to answer the following open-ended question: "If you had to explain to a peer who doesn't know your teacher how he or she communicates in class, what would you tell them?". Sentiment analysis was performed using Microsoft's pre-trained model. The reliability of the measure was estimated between the tool and one of the researchers who coded all answers independently. The Cohen's kappa and the average pairwise percent agreement were estimated with ReCal2. Cohen's kappa was .68, and the agreement reached was 90.8%, both considered satisfactory. To test the hypothesis relations among SA and students' emotional engagement, a structural equation model (SEM) was estimated. Results demonstrated a good fit of the data: RMSEA = .04, SRMR = .03, TLI = .99, CFI = .99. Specifically, the results showed that student’s sentiment regarding their teachers’ teaching positively predicted their emotional engagement (β == .16 [.02, -.30]). In other words, when students' opinion toward their instructors' teaching practices is positive, it is more likely for students to engage emotionally in the subject. Altogether, the results show a promising future for sentiment analysis techniques in the field of education. They suggest the usefulness of this tool when evaluating relations among teaching practices and student outcomes.

Keywords: sentiment analysis, students' evaluation of teaching, structural-equation modelling, emotional engagement

Procedia PDF Downloads 55

Authors: Rui Yin, Haojie Wang, Xun Li

Abstract:

Recently, mainstream dense retrieval methods have obtained state-of-the-art results on some datasets and tasks. However, they require large amounts of training data, which is not available in most domains. The severe performance degradation of dense retrievers on new data domains has limited the use of dense retrieval methods to only a few domains with large training datasets. In this paper, we propose an unsupervised domain-adaptive approach based on query generation. First, a generative model is used to generate relevant queries for each passage in the target corpus, and then the generated queries are used for mining negative passages. Finally, the query-passage pairs are labeled with a cross-encoder and used to train a domain-adapted dense retriever. Experiments show that our approach is more robust than previous methods in target domains that require less unlabeled data.

Keywords: dense retrieval, query generation, unsupervised training, text retrieval

Procedia PDF Downloads 38

Authors: Elisa Santana-Monagas, Juan L. Núñez, Jaime León, Samuel Falcón, Celia Fernández, Rocío P. Solís

Abstract:

Students’ emotional experiences have been a widely discussed theme among researchers, proving a central role on students’ outcomes. Yet, up to now, far too little attention has been paid to teaching practices that negatively relate with students’ negative emotions in the higher education. The present work aims to examine the relationship between teachers’ teaching practices (i.e., students’ evaluations of teaching and autonomy support), the students’ feelings of boredom and agentic engagement and motivation in the higher education context. To do so, the present study incorporates one of the most popular tools in natural processing language to address students’ evaluations of teaching: sentiment analysis. Whereas most research has focused on the creation of SA models and assessing students’ satisfaction regarding teachers and courses to the author’s best knowledge, no research before has included results from SA into an explanatory model. A total of 225 university students (Mean age = 26.16, SD = 7.4, 78.7 % women) participated in the study. Students were enrolled in degree and masters’ studies at the faculty of Education of a public university of Spain. Data was collected using an online questionnaire students could access through a QR code they completed during a teaching period where the assessed teacher was not present. To assess students’ sentiments towards their teachers’ teaching, we asked them the following open-ended question: “If you had to explain a peer who doesn't know your teacher how he or she communicates in class, what would you tell them?”. Sentiment analysis was performed with Microsoft's pre-trained model. For this study, we relied on the probability of the students answer belonging to the negative category. To assess the reliability of the measure, inter-rater agreement between this NLP tool and one of the researchers, who independently coded all answers, was examined. The average pairwise percent agreement and the Cohen’s kappa were calculated with ReCal2. The agreement reached was of 90.8% and Cohen’s kappa .68, both considered satisfactory. To test the hypothesis relations a structural equation model (SEM) was estimated. Results showed that the model fit indices displayed a good fit to the data; χ² (134) = 351.129, p < .001, RMSEA = .07, SRMR = .09, TLI = .91, CFI = .92. Specifically, results show that boredom was negatively predicted by autonomy support practices (β = -.47[-.61, -.33]), whereas for the negative sentiment extracted from SET, this relation was positive (β = .23[.16, .30]). In other words, when students’ opinion towards their instructors’ teaching practices was negative, it was more likely for them to feel bored. Regarding the relations among boredom and student outcomes, results showed a negative predictive value of boredom on students’ motivation to study (β = -.46[-.63, -.29]) and agentic engagement (β = -.24[-.33, -.15]). Altogether, results show a promising future for sentiment analysis techniques in the field of education as they proved the usefulness of this tool when evaluating relations among teaching practices and student outcomes.

Keywords: sentiment analysis, boredom, motivation, agentic engagement

Procedia PDF Downloads 66

Authors: Ivana Lolic, Petar Soric, Mirjana Cizmesija

Abstract:

Based on Business and Consumer Survey (BCS) data, the European Commission (EC) regularly publishes the monthly Economic Sentiment Indicator (ESI) for each EU member state. ESI is conceptualized as a leading indicator, aimed ad tracking the overall economic activity. In calculating ESI, the EC employs arbitrarily chosen weights on 15 BCS response balances. This paper raises the predictive quality of ESI by applying nonlinear programming to find such weights that maximize the correlation coefficient of ESI and year-on-year GDP growth. The obtained results show that the highest weights are assigned to the response balances of industrial sector questions, followed by questions from the retail trade sector. This comes as no surprise since the existing literature shows that the industrial production is a plausible proxy for the overall Croatian economic activity and since Croatian GDP is largely influenced by the aggregate personal consumption.

Keywords: business and consumer survey, economic sentiment indicator, leading indicator, nonlinear optimization with constraints

Procedia PDF Downloads 434

Authors: Rik van Leeuwen, Ger Koole

Abstract:

Within hospitality, marketing departments use segmentation to create tailored strategies to ensure personalized marketing. This study provides a data-driven approach by segmenting guest profiles via hierarchical clustering based on an extensive set of features. The industry requires understandable outcomes that contribute to adaptability for marketing departments to make data-driven decisions and ultimately driving profit. A marketing department specified a business question that guides the unsupervised machine learning algorithm. Features of guests change over time; therefore, there is a probability that guests transition from one segment to another. The purpose of the study is to provide steps in the process from raw data to actionable insights, which serve as a guideline for how hospitality companies can adopt an algorithmic approach.

Keywords: hierarchical cluster analysis, hospitality, market segmentation

Procedia PDF Downloads 76

Authors: Derek Brandon G. Yu, Clyde Vincent O. Pilapil, Christine F. Peña

Abstract:

College students of Cebu province have been indoors since March 2020, and a challenge encountered is the sudden shift from face to face to online learning and with the lack of empirical data on online learning on Higher Education Institutions (HEIs) in the Philippines. Sentiments on face to face and online learning will be collected from University of San Carlos (USC), School of Arts and Sciences (SAS) students regarding Mathematics in the Modern World (MMW), a General Education (GE) course. Natural Language Processing with machine learning algorithms will be used to classify the sentiments of the students. Results of the research study are the themes identified through topic modelling and the overall sentiments of the students in USC SAS

Keywords: natural language processing, online learning, sentiment analysis, topic modelling

Procedia PDF Downloads 207

Authors: M. A. T. AlSudairi, T. G. K. Vasista

Abstract:

The concept of social media is becoming the top of the agenda for many business executives and public sector executives today. Decision makers as well as consultants, try to identify ways in which firms and enterprises can make profitable use of social media and network related applications such as Wikipedia, Face book, YouTube, Google+, Twitter. While it is fun and useful to participating in this media and network for achieving the communication effectively and efficiently, semantic and sentiment analysis and interpretation becomes a crucial issue. So, the objective of this paper is to provide literature review on social media, network and related technology related to semantics and sentiment or opinion analysis covering business and governance perspectives. In this regard, a case study on the use and adoption of Social media in Saudi Arabia has been discussed. It is concluded that semantic web technology play a significant role in analyzing the social networks and social media content for extracting the interpretational knowledge towards strategic decision support.

Keywords: CRASP methodology, formative assessment, literature review, semantic web services, social media, social networks

Procedia PDF Downloads 421

Authors: Xiuying Wang, Changliang Li, Bo Xu

Abstract:

A fixed-length feature vector is required for many machine learning algorithms in NLP field. Word embeddings have been very successful at learning lexical information. However, they cannot capture the compositional meaning of sentences, which prevents them from a deeper understanding of language. In this paper, we introduce a novel hierarchical tree long short-term memory (HTLSTM) model that learns vector representations for sentences of arbitrary syntactic type and length. We propose to split one sentence into three hierarchies: short phrase, long phrase and full sentence level. The HTLSTM model gives our algorithm the potential to fully consider the hierarchical information and long-term dependencies of language. We design the experiments on both English and Chinese corpus to evaluate our model on sentiment analysis task. And the results show that our model outperforms several existing state of the art approaches significantly.

Keywords: deep learning, hierarchical tree long short-term memory, sentence representation, sentiment analysis

Procedia PDF Downloads 328

Authors: Cindy Agyemang

Abstract:

This study seeks to find out if racial sentiment toward immigrants still matters in the United States with COVID-19 present. It is argued that previous studies on immigration and racial attitudes or race conducted do not consider how health-related pandemics influence public opinion on immigration and the racial attitudes of people during severe health-related pandemics. In doing so, this paper hypothesizes that respondents' racial sentiment towards immigrants during this pandemic will influence their views on opposing immigration, those that believe the president handled cases on COVID-19 better are more likely to oppose immigration, and party affiliation affects respondents' views on immigration and COVID-19. For testing these hypotheses, the 2012, 2016, and 2020 American National Election Studies data was used. In accordance with the expectations of this study, it was observed that there was a statistically significant relationship between all my estimated models. This paper concludes that racial sentiment toward immigrants still matters even more in the United States, especially with the existence of health-related pandemics.

Keywords: COVID-19, immigration, racial attitudes, partisanship

Procedia PDF Downloads 251

Authors: Zhi Hao Chow, Cian Mulligan, Jack Walsh, Antonio Garzon Vico, Dimitar Krastev

Abstract:

Drug development is resource-intensive, time-consuming, and increasingly expensive with each developmental stage. The success rates of drug development are also relatively low, and the resources committed are wasted with each failed candidate. As such, a reliable method of predicting the success of drug development is in demand. The hypothesis was that some examples of failed drug candidates are pushed through developmental pipelines based on false confidence and may possess common linguistic features identifiable through sentiment analysis. Here, the concept of using text analysis to discover such features in research publications and investor reports as predictors of success was explored. R studios were used to perform text mining and lexicon-based sentiment analysis to identify affective phrases and determine their frequency in each document, then using SPSS to determine the relationship between our defined variables and the accuracy of predicting outcomes. A total of 161 publications were collected and categorised into 4 groups: (i) Cancer treatment, (ii) Neurodegenerative disease treatment, (iii) Vaccines, and (iv) Others (containing all other drugs that do not fit into the 3 categories). Text analysis was then performed on each document using 2 separate datasets (BING and AFINN) in R within the category of drugs to determine the frequency of positive or negative phrases in each document. A relative positivity and negativity value were then calculated by dividing the frequency of phrases with the word count of each document. Regression analysis was then performed with SPSS statistical software on each dataset (values from using BING or AFINN dataset during text analysis) using a random selection of 61 documents to construct a model. The remaining documents were then used to determine the predictive power of the models. Model constructed from BING predicts the outcome of drug performance in clinical trials with an overall percentage of 65.3%. AFINN model had a lower accuracy at predicting outcomes compared to the BING model at 62.5% but was not effective at predicting the failure of drugs in clinical trials. Overall, the study did not show significant efficacy of the model at predicting outcomes of drugs in development. Many improvements may need to be made to later iterations of the model to sufficiently increase the accuracy.

Keywords: data analysis, drug development, sentiment analysis, text-mining

Procedia PDF Downloads 124

Authors: Ahmad Alwosheel, Ahmed Alqaraawi

Abstract:

This work proposes a new speaker segmentation approach for two speakers. It is an online approach that does not require a prior information about speaker models. It has two phases, a conventional approach such as unsupervised BIC-based is utilized in the first phase to detect speaker changes and train a Neural Network, while in the second phase, the output trained parameters from the Neural Network are used to predict next incoming audio stream. Using this approach, a comparable accuracy to similar BIC-based approaches is achieved with a significant improvement in terms of computation time.

Keywords: artificial neural network, diarization, speaker indexing, speaker segmentation

Procedia PDF Downloads 468

Authors: Luyao Zhang, Tianyu Wu, Jiayi Li, Carlos-Gustavo Salas-Flores, Saad Lahrichi

Abstract:

Recent advances in AI have made algorithmic trading a central role in finance. However, current research and applications are disconnected information islands. We propose a generally applicable pipeline for designing, programming, and evaluating algorithmic trading of stock and crypto tokens. Moreover, we provide comparative case studies for four conventional algorithms, including moving average crossover, volume-weighted average price, sentiment analysis, and statistical arbitrage. Our study offers a systematic way to program and compare different trading strategies. Moreover, we implement our algorithms by object-oriented programming in Python3, which serves as open-source software for future academic research and applications.

Keywords: algorithmic trading, AI for finance, fintech, machine learning, moving average crossover, volume weighted average price, sentiment analysis, statistical arbitrage, pair trading, object-oriented programming, python3

Procedia PDF Downloads 113

Authors: G. C. Joshi, M. Paul, B. K. Kalita, V. Ranga, J. S. Rawat, P. S. Rawat

Abstract:

Being a habitat of the global village, every place has established connection through the strength and power of social media piercing through the political boundaries. Social media is a digital platform, where people across the world can interact as it has advantages of being universal, anonymous, easily accessible, indirect interaction, gathering and sharing information. The power of social media lies in the intensity of sharing extreme opinions or feelings, in contrast to the personal interactions which can be easily mapped in the form of Sentiment Mapping. The easy access to social networking sites such as Facebook, Twitter and blogs made unprecedented opportunities for citizens to voice their opinions loaded with dynamics of emotions. These further influence human thoughts where social media plays a very active role. A recent incident of public importance was selected as a case study to map the sentiments of people through Twitter. Understanding those dynamics through the eye of an ordinary people can be challenging. With the help of R-programming language and by the aid of GIS techniques sentiment maps has been produced. The emotions flowing worldwide in the form of tweets were extracted and analyzed. The number of tweets had diminished by 91 % from 25/08/2017 to 31/08/2017. A boom of sentiments emerged near the origin of the case, i.e., Delhi, Haryana and Punjab and the capital showed maximum influence resulting in spillover effect near Delhi. The trend of sentiments was prevailing more as neutral (45.37%), negative (28.6%) and positive (21.6%) after calculating the sentiment scores of the tweets. The result can be used to know the spatial distribution of digital penetration in India, where highest concentration lies in Mumbai and lowest in North East India and Jammu and Kashmir.

Keywords: sentiment mapping, digital literacy, GIS, R statistical language, spatio-temporal

Procedia PDF Downloads 123

Authors: Renukswamy Chikkamath, Vishvapalsinhji Ramsinh Parmar, Christoph Hewel, Markus Endres

Abstract:

Given a patent document, identifying distinct semantic annotations is an interesting research aspect. Text annotation helps the patent practitioners such as examiners and patent attorneys to quickly identify the key arguments of any invention, successively providing a timely marking of a patent text. In the process of manual patent analysis, to attain better readability, recognising the semantic information by marking paragraphs is in practice. This semantic annotation process is laborious and time-consuming. To alleviate such a problem, we proposed a dataset to train machine learning algorithms to automate the highlighting process. The contributions of this work are: i) we developed a multi-class dataset of size 150k samples by traversing USPTO patents over a decade, ii) articulated statistics and distributions of data using imperative exploratory data analysis, iii) baseline Machine Learning models are developed to utilize the dataset to address patent paragraph highlighting task, and iv) future path to extend this work using Deep Learning and domain-specific pre-trained language models to develop a tool to highlight is provided. This work assists patent practitioners in highlighting semantic information automatically and aids in creating a sustainable and efficient patent analysis using the aptitude of machine learning.

Keywords: machine learning, patents, patent sentiment analysis, patent information retrieval

Procedia PDF Downloads 63

Authors: Deeman Yousif Mahmood, Mohammed Abdullah Hussein

Abstract:

The goal of a network-based intrusion detection system is to classify activities of network traffics into two major categories: normal and attack (intrusive) activities. Nowadays, data mining and machine learning plays an important role in many sciences; including intrusion detection system (IDS) using both supervised and unsupervised techniques. However, one of the essential steps of data mining is feature selection that helps in improving the efficiency, performance and prediction rate of proposed approach. This paper applies unsupervised K-means clustering algorithm with information gain (IG) for feature selection and reduction to build a network intrusion detection system. For our experimental analysis, we have used the new NSL-KDD dataset, which is a modified dataset for KDDCup 1999 intrusion detection benchmark dataset. With a split of 60.0% for the training set and the remainder for the testing set, a 2 class classifications have been implemented (Normal, Attack). Weka framework which is a java based open source software consists of a collection of machine learning algorithms for data mining tasks has been used in the testing process. The experimental results show that the proposed approach is very accurate with low false positive rate and high true positive rate and it takes less learning time in comparison with using the full features of the dataset with the same algorithm.

Keywords: information gain (IG), intrusion detection system (IDS), k-means clustering, Weka

Procedia PDF Downloads 263

Authors: Oussama Hafferssas, Hiba Benyahia, Amina Madani, Nassima Zeriri

Abstract:

Although data nowadays has multiple forms; from text to images, and from audio to videos, yet text is still the most used one at a public level. At an academical and research level, and unlike other forms, text can be considered as the easiest form to process. Therefore, a brunch of Data Mining researches has been always under its shadow, called "Text Mining". Its concept is just like data mining’s, finding valuable patterns in data, from large collections and tremendous volumes of data, in this case: Text. Named entity recognition (NER) is one of Text Mining’s disciplines, it aims to extract and classify references such as proper names, locations, expressions of time and dates, organizations and more in a given text. Our approach "Octopub" does not aim to find new ways to improve named entity recognition process, rather than that it’s about finding a new, and yet smart way, to use NER in a way that we can extract sentiments of millions of people using Social Networks as a limitless information source, and Marketing for product promotion as the main domain of application.

Keywords: textmining, named entity recognition(NER), sentiment analysis, social media networks (SN, SMN), business intelligence(BI), marketing

Procedia PDF Downloads 558

Authors: Jummalla Aashrith, N. L. Shiva Sai, K. Bhavya Sri

Abstract:

The swift progress of web technology has not only amassed a vast reservoir of internet data but also triggered a substantial surge in data generation. The internet has metamorphosed into one of the dynamic hubs for online education, idea dissemination, as well as opinion-sharing. Notably, the widely utilized social networking platform Twitter is experiencing considerable expansion, providing users with the ability to share viewpoints, participate in discussions spanning diverse communities, and broadcast messages on a global scale. The upswing in online engagement has sparked a significant curiosity in subjective analysis, particularly when it comes to Twitter data. This research is committed to delving into sentiment analysis, focusing specifically on the realm of Twitter. It aims to offer valuable insights into deciphering information within tweets, where opinions manifest in a highly unstructured and diverse manner, spanning a spectrum from positivity to negativity, occasionally punctuated by neutrality expressions. Within this document, we offer a comprehensive exploration and comparative assessment of modern approaches to opinion mining. Employing a range of machine learning algorithms such as Naive Bayes and Logistic Regression, our investigation plunges into the domain of Twitter data streams. We delve into overarching challenges and applications inherent in the realm of subjectivity analysis over Twitter.

Keywords: machine learning, sentiment analysis, visualisation, python

Procedia PDF Downloads 24

Authors: Ahmad Alwosheel, Ahmed Alqaraawi

Abstract:

This work proposes an unsupervised text-independent probabilistic approach to recognize Quran reciter voice. It is an accurate approach that works on real time applications. This approach does not require a prior information about reciter models. It has two phases, where in the training phase the reciters' acoustical features are modeled using Gaussian Mixture Models, while in the testing phase, unlabeled reciter's acoustical features are examined among GMM models. Using this approach, a high accuracy results are achieved with efficient computation time process.

Keywords: Quran, speaker recognition, reciter recognition, Gaussian Mixture Model

Procedia PDF Downloads 352

Authors: Samuel Munaf, Kevin Swingler, Franz Brülisauer, Anthony O’Hare, George Gunn, Aaron Reeves

Abstract:

Web scraping and text mining are popular computer science methods deployed by public health researchers to augment traditional epidemiological surveillance. However, within veterinary disease surveillance, such techniques are still in the early stages of development and have not yet been fully utilised. This study presents an exploration into the utility of incorporating internet-based data to better understand the smallholder farming communities within Scotland by using online text extraction and the subsequent mining of this data. Web scraping of the livestock fora was conducted in conjunction with text mining of the data in search of common themes, words, and topics found within the text. Results from bi-grams and topic modelling uncover four main topics of interest within the data pertaining to aspects of livestock husbandry: feeding, breeding, slaughter, and disposal. These topics were found amongst both the poultry and pig sub-forums. Topic modeling appears to be a useful method of unsupervised classification regarding this form of data, as it has produced clusters that relate to biosecurity and animal welfare. Internet data can be a very effective tool in aiding traditional veterinary surveillance methods, but the requirement for human validation of said data is crucial. This opens avenues of research via the incorporation of other dynamic social media data, namely Twitter and Facebook/Meta, in addition to time series analysis to highlight temporal patterns.

Keywords: veterinary epidemiology, disease surveillance, infodemiology, infoveillance, smallholding, social media, web scraping, sentiment analysis, geolocation, text mining, NLP

Procedia PDF Downloads 66

Authors: Chien-Hung Chen, Yan-Chun Hsing, Yung-Chun Chang

Abstract:

The Internet has grown into a powerful medium for information dispersion and social interaction that leads to a rapid growth of social media which allows users to easily post their emotions and perspectives regarding certain topics online. Our research aims at using natural language processing and text mining techniques to explore the public emotions expressed on Twitter by analyzing the sentiment behind tweets. In this paper, we propose a composite kernel method that integrates tree kernel with the linear kernel to simultaneously exploit both the tree representation and the distributed emotion keyword representation to analyze the syntactic and content information in tweets. The experiment results demonstrate that our method can effectively detect public emotion of tweets while outperforming the other compared methods.

Keywords: emotion recognition, natural language processing, composite kernel, sentiment analysis, text mining

Procedia PDF Downloads 193