Search results for: sentiment%20analysis

Authors: Heba M. Wagih, Hoda M. O. Mokhtar

Abstract:

Social Network has recently played a significant role in both scientific and social communities. The growing adoption of social network applications has been a relevant source of information nowadays. Due to its popularity, several research trends are emerged to service the huge volume of users including, Location-Based Social Networks (LBSN), Recommendation Systems, Sentiment Analysis Applications, and many others. LBSNs applications are among the highly demanded applications that do not focus only on analyzing the spatiotemporal positions in a given raw trajectory but also on understanding the semantics behind the dynamics of the moving object. LBSNs are possible means of predicting human mobility based on users social ties as well as their spatial preferences. LBSNs rely on the efficient representation of users’ trajectories. Hence, traditional raw trajectory information is no longer convenient. In our research, we focus on studying human behavior trajectory which is the major pillar in location recommendation systems. In this paper, we propose an ontology design patterns with their underlying description logics to efficiently annotate human behavior trajectories.

Keywords: human behavior trajectory, location-based social network, ontology, social network

Procedia PDF Downloads 425

Authors: Seba Quqandi

Abstract:

This study investigates the bond that people form using their assistive devices and the tactics applied during the product design process to help improve the user experience leading to a long-term product relationship. The aim is to develop a conceptual framework with which to describe and analyze the bond people form with their assistive devices and to integrate human emotions as a factor during the development of the product design process. The focus will be on the assistive technology market, namely, the Aid-For-Daily-Living market for situational impairments, to increase the quality of wellbeing. Findings will help us better understand the real issues of the product experience concerning people’s interaction throughout the product performance, establish awareness of the emotional effects in the daily interaction that fosters the product attachment, and help product developers and future designers create a connection between users and their assistive devices. The research concludes by discussing the implications of these findings for professionals and academics in the form of experiments in order to identify new areas that can stimulate new /or developed design directions.

Keywords: experience design, interaction design, emotion, design psychology, assistive tools, customization, userentred design

Procedia PDF Downloads 190

Authors: Syed Basit Ali Shah Bukhari, Yan Qiang, Saad Abdul Rauf, Syed Saqlaina Bukhari

Abstract:

Text Classification is the methodology to classify any given text into the respective category from a given set of categories. It is highly important and vital to use proper set of pre-processing , feature selection and classification techniques to achieve this purpose. In this paper we have used different ensemble techniques along with variance in feature selection parameters to see the change in overall accuracy of the result and also on some other individual class based features which include precision value of each individual category of the text. After subjecting our data through pre-processing and feature selection techniques , different individual classifiers were tested first and after that classifiers were combined to form ensembles to increase their accuracy. Later we also studied the impact of decreasing the classification categories on over all accuracy of data. Text classification is highly used in sentiment analysis on social media sites such as twitter for realizing people’s opinions about any cause or it is also used to analyze customer’s reviews about certain products or services. Opinion mining is a vital task in data mining and text categorization is a back-bone to opinion mining.

Keywords: Natural Language Processing, Ensemble Classifier, Bagging Classifier, AdaBoost

Procedia PDF Downloads 205

Authors: Ricky Leung

Abstract:

Artificial intelligence (AI) and machine learning (ML) have revolutionized the way health organizations approach social media. The sheer volume of data generated through social media can be overwhelming, but AI and ML can help organizations effectively manage this information to improve the health and well-being of individuals and communities. One way AI can be used to enhance social media in health organizations is through sentiment analysis. This involves analyzing the emotions expressed in social media posts to better understand public opinion and respond accordingly. This can help organizations gauge the impact of their campaigns, track the spread of misinformation, and improve communication with the public. While social media is a useful tool, researchers and practitioners have expressed fear that it will be used for the spread of misinformation, which can have serious consequences for public health. Health organizations must work to ensure that AI systems are transparent, trustworthy, and unbiased so they can help minimize the spread of misinformation. In conclusion, AI and ML have the potential to greatly enhance the use of social media in health organizations. These technologies can help organizations effectively manage large amounts of data and understand stakeholders' sentiments. However, it is important to carefully consider the potential consequences and ensure that these systems are carefully designed to minimize the spread of misinformation.

Keywords: AI, ML, social media, health organizations

Procedia PDF Downloads 63

Authors: Izzudin Busnaina

Abstract:

An important question for marketers in the international arena is whether the consumer’s responses (i.e., sentiment and behavioral aspects) toward the global marketing programs in developing countries depend on culture. In a study representing a large sample of consumers and four different home appliances country-of-origin global operators in Libya, the author explores the potential role of culture on Arab consumers' responses toward foreign marketing programs. Results indicate that although the foreign companies have a tendency to adopted standardization perspective, this does not impact on consumers’ responses in a single cultural context toward marketing. The findings reveal that buying behavior was more a function of individual difference than of national cultural context. Further, the results suggest that for mainstream home appliances, segmenting on the basis of nationality is probably unnecessary and that a standardized approach would likely be successful across an increasingly relevant Arab world; and that continuing perceptions of Arab insularity are likely to be misplaced. Faced with the effectiveness of globally efficient marketing programs, local manufacturers would need to work hard to identify particular niche segments where a culturally-specific appeal might be more successful.

Keywords: arab world, buyer’s characteristics, consumer behavior, home appliances, marketing program

Procedia PDF Downloads 368

Authors: Nnaemeka Enemchukwu

Abstract:

In modern-day Nigeria, the spirit of Biafra, the defunct secessionist state of former Eastern Nigeria, endures. While some attempt to downplay the historical factors that led to its creation, this paper aims to demonstrate that the 1966 pogroms in Nigeria, which claimed the lives of over 30,000 Igbo people, shattered their faith in the nation's ability to provide security and acceptance. This loss of faith led to a mass exodus from various regions of the country back to their homeland in Eastern Nigeria. Utilizing primary sources such as interviews and archival reports, and secondary sources like books, journals, and websites, this paper will argue that the trauma and terror of the 1966 massacres were the primary drivers of secessionist sentiment and self-determination among the Igbo people, ultimately leading to the declaration of Biafra. By drawing parallels with other historical incidents across the globe, this paper will establish the theoretical connection between shocking events, identity questioning among traumatized groups, and the subsequent rise of nationalistic sentiments seeking to ensure group preservation. To achieve its objective, this paper will employ descriptive, narrative, and chronological methods of analysis to present and discuss its findings.

Keywords: Igbo, pogrom, shock, trauma, nationalism, Biafra

Procedia PDF Downloads 32

Authors: Papazafeiropoulou Olga

Abstract:

The first Greek expatriates created centers of culture in Australia from the beginning of the 19th century, in the large urban centers of the cities (Sydney, Melbourne, Brisbane, Adelaide, Perth). They created community theater according to their cultural standards, their socio-spiritual progress and development and their relationship with theatrical creation. At the same time, the Greek immigrants of the small towns and, especially of NSW, created their own temples of art, rebuilding theater buildings (theatres and cinemas), many of which are preserved to this day. Hellenism in Australia operated in the field of entertainment, reflecting the currents of the time and the global spread of mechanical developments. The Australian-born young people of the parish, as well as pioneering expatriates joined the theater and cinematographic events of Australia. They mobilized beyond the narrow confines of the parish, gaining recognition and projecting Hellenism to the Australian establishment. G. Paizis (A. Haggard), Dimitrios Ioannidis, Stelios Saligaros, Angela Parselli, Sofia Pergamali, Raoul Kardamatis, Adam Tavlaridis, John Lemonne, Rudy Ricco, Artemis Linou, distinguished themselves by writing their names in the history of Australian theater, as they served consequently the theatrical process, elevating the sentiment of the expatriate during the early years of its settlement in the Australian Commonwealth until 1950.

Keywords: greeks, commubity, australia, theatre

Procedia PDF Downloads 34

Authors: Amartya Hatua, Trung Nguyen, Andrew Sung

Abstract:

In this paper, we study the information diffusion process on Twitter as a multivariate time series problem. Our model concerns three measures (volume, network influence, and sentiment of tweets) based on 10 features, and we collected 27 million tweets to build our information diffusion time series dataset for analysis. Then, different time series clustering techniques with Dynamic Time Warping (DTW) distance were used to identify different patterns of information diffusion. Finally, we built the information diffusion prediction models for new hashtags which comprise two phrases: The first phrase is recognizing the pattern using k-NN with DTW distance; the second phrase is building the forecasting model using the traditional Autoregressive Integrated Moving Average (ARIMA) model and the non-linear recurrent neural network of Long Short-Term Memory (LSTM). Preliminary results of performance evaluation between different forecasting models show that LSTM with clustering information notably outperforms other models. Therefore, our approach can be applied in real-world applications to analyze and predict the information diffusion characteristics of selected topics or memes (hashtags) in Twitter.

Keywords: ARIMA, DTW, information diffusion, LSTM, RNN, time series clustering, time series forecasting, Twitter

Procedia PDF Downloads 361

Authors: Tsai-Hsiu Lin

Abstract:

Dan C. Lortie’s Schoolteacher: A sociological study is one of the best works on the sociology of teaching since W. Waller’s classic study. It is a book worthy of review. Following the tradition of symbolic interactionists, Lortie demonstrated the qualities who studied the occupation of teaching. Using several methods to gather effective data, Lortie has portrayed the ethos of the teaching profession. Therefore, the work is an important book on the teaching profession and teacher culture. Though outstanding, Lortie’s work is also flawed in that his perspectives and methodology were adopted largely from symbolic interactionism. First, Lortie in his work analyzed many points regarding teacher culture; for example, he was interested in exploring “sentiment,” “cathexis,” and “ethos.” Thus, he was more a psychologist than a sociologist. Second, symbolic interactionism led him to discern the teacher culture from a micro view, thereby missing the structural aspects. For example, he did not fully discuss the issue of gender and he ignored the issue of race. Finally, following the qualitative sociological tradition, Lortie employed many qualitative methods to gather data but only foucused on obtaining and presenting interview data. Moreover, he used measurement methods that were too simplistic for analyzing quantitative data fully.

Keywords: education reform, teacher culture, teaching profession, Lortie’s Schoolteacher

Procedia PDF Downloads 206

Authors: Chananart Meenanan

Abstract:

The composition Isan Symphonic Variations for Chorus and Orchestra is a musical composition inspired by Isan Folk music tunes. The composer has created the well crafted melodic variations and cultural sound character of the piece based on the Klon Lum Tang Isan Keaw (Green Isan’s short poems). Meanwhile, the poetic lyric has been motivatedly recreated to bring the abundance of Northeastern Thailand region’s sentiment back to life. Moreover, the sound of xylophone (Ponglang), the instruments of the orchestra and the chorus were blended in order to present Isan folk music’s character via the Western musical idiom. The 3 movement of this composition is divided as following: In Movement I (Allegro), the introduction has been represented the uniqueness in Isan folk music’s liveliness by expressing it through the sound of chorus and orchestra. The composer also added the melodious sound flavor by utilizing the variety of the muting sound style on trumpets and horns. In Movement II (Moderato), the aspect of the heterophonic approach music has been implied to the main idea of the entire movement whereby its formatted transformation worked effectively through chorus and the orchestra. In Movement III (Allegretto) the harmonic chromaticism was modified and applied as the symbolic icon of the entire movement. The transparence of Isan cultural sound was perfectly designed to be the highlight of this spectacular episode.

Keywords: Isan, symphonic variations, chorus, orchestra

Procedia PDF Downloads 221

Authors: Kanika Sood, Sijie Shang

Abstract:

A fundamental goal of education includes preparing students to become a part of the global workforce by making beneficial contributions to society. In this paper, we analyze student performance for multiple courses that involve different teaching pedagogies: a cooperative learning technique and an inquiry-based learning strategy. Student performance includes student engagement, grades, and attendance records. We perform this study in the Computer Science department for online and in-person courses for 450 students. We will perform correlation analysis to study the relationship between student scores and other parameters such as gender, mode of learning. We use natural language processing and machine learning to analyze student feedback data and performance data. We assess the learning outcomes of two teaching pedagogies for undergraduate and graduate courses to showcase the impact of pedagogical adoption and learning outcome as determinants of academic achievement. Early findings suggest that when using the specified pedagogies, students become experts on their topics and illustrate enhanced engagement with peers.

Keywords: bag-of-words, cooperative learning, education, inquiry-based learning, in-person learning, natural language processing, online learning, sentiment analysis, teaching pedagogy

Procedia PDF Downloads 46

Authors: Levi Corallo

Abstract:

Typed language made by humans on computers and cell phones has made a significant distinction from previous modes of written language exchanges. While acronyms remain one of the most predominant markings of typed language, another and perhaps more recent revolution in the way humans communicate has been with the use of symbols or glyphs, primarily Emojis—globally introduced on the iPhone keyboard by Apple in 2008. This paper seeks to analyze the use of symbols in typed communication from both a linguistic and machine learning perspective. The Unicode system will be explored and methods of encoding will be juxtaposed with the current machine and human perception. Topics in how typed symbol usage exists in conversation will be explored as well as topics across current research methods dealing with Emojis like sentiment analysis, predictive text models, and so on. This study proposes that sequential analysis is a significant feature for analyzing unicode characters in a corpus with machine learning. Current models that are trying to learn or translate the meaning of Emojis should be starting to learn using bi- and tri-grams of Emoji, as well as observing the relationship between combinations of different Emoji in tandem. The sociolinguistics of an entire new vernacular of language referred to here as ‘typed language’ will also be delineated across my analysis with unicode glyphs from both a semantic and technical perspective.

Keywords: unicode, text symbols, emojis, glyphs, communication

Procedia PDF Downloads 169

Authors: Fernanda Conforto de Oliveira

Abstract:

The International Monetary Fund (IMF) has a central role in global financial governance as the world’s leading crisis lender. Its practice of conditional lending – conditioning loans on the implementation of economic policy adjustments – is the primary lever by which the institution interacts with and influences the policy choices of member countries and has been a key topic of interest to scholars and public opinion. However, empirical evidence about the economic and (geo)political determinants of IMF lending behavior remains inconclusive, and no model that explains IMF policies has been identified. This research moves beyond panel analysis to focus on financial negotiations for the first IMF programs in Argentina and Brazil in the early post-war period. It seeks to understand why negotiations achieved distinct objectives: Argentinean officials cooperated and complied with IMF policies, whereas their Brazilian counterparts hesitated. Using qualitative and automated text analysis, this paper analyses the hypothesis about whether a differential IMF treatment could help to explain these distinct outcomes. This paper contributes to historical studies on IMF-Latin America relations and the broader literature in international policy economy about IMF policies.

Keywords: international monetary fund, international history, financial history, Latin American economic history, natural language processing, sentiment analysis

Procedia PDF Downloads 27

Authors: Zamri Abu Bakar Zamri, Normaly Kamal Ismail Normaly, Mohd Izani Mohamed Rawi Izani

Abstract:

Malay noun compound are phrases that consist of two or more nouns. The key characteristic behind noun compounds lies on its frequent occurrences within the text. Therefore, extracting these noun compounds is essential for several domains of research such as Information Retrieval, Sentiment Analysis and Question Answering. Many research efforts have been proposed in terms of extracting Malay noun compounds using linguistic and statistical approaches. Most of the existing methods have concentrated on the extraction of bi-gram noun+noun compound. However, extracting noun+verb, noun+adjective and noun+prepositional is challenging due to the difficulty of selecting an appropriate method with effective results. Thus, there is still room for improvement in terms of enhancing the effectiveness of compound word extraction. Therefore, this study proposed a combination of linguistic approach and statistical measures in order to enhance the extraction of compound words. Several preprocessing steps are involved including normalization, tokenization, and stemming. The linguistic approach that has been used in this study is Part-of-Speech (POS) tagging. In addition, a new linguistic pattern for named entities has been utilized using a list of Malays named entities in order to enhance the linguistic approach in terms of noun compound recognition. The proposed statistical measures consists of NC-value, NTC-value and NLC value.

Keywords: Compound Word, Noun Compound, Linguistic Approach, Statistical Approach

Procedia PDF Downloads 317

Authors: Oshin Anand, Atanu Rakshit

Abstract:

The vast increment in the e-commerce ventures makes this area a prominent research stream. Besides several quantified parameters, the textual content of reviews is a storehouse of many information that can educate companies and help them earn profit. This study is an attempt in this direction. The article attempts to categorize data based on a computed metric that quantifies the influencing capacity of reviews rendering two categories of high and low influential reviews. Further, each of these document is studied to conclude several product feature categories. Each of these categories along with the computed metric is converted to linguistic identifiers and are used in an association mining model. The article makes a novel attempt to combine feature attraction with quantified metric to categorize review text and finally provide frequent patterns that depict customer preferences. Frequent mentions in a highly influential score depict customer likes or preferred features in the product whereas prominent pattern in low influencing reviews highlights what is not important for customers. This is achieved using a hybrid approach of text mining for feature and term extraction, sentiment analysis, multicriteria decision-making technique and association mining model.

Keywords: association mining, customer preference, frequent pattern, online reviews, text mining

Procedia PDF Downloads 363

Authors: Raymond Xu, Cindy Jingru Wang

Abstract:

Social media has become a globally connected and influencing platform. Social media data, such as tweets, can help predict the spread of pandemics and provide individuals and healthcare providers early warnings. Public psychological reactions and opinions can be efficiently monitored by AI models on the progression of dominant topics on Twitter. However, statistics show that as the coronavirus spreads, so does an infodemic of misinformation due to pandemic-related factors such as unemployment and lockdowns. Social media algorithms are often biased toward outrage by promoting content that people have an emotional reaction to and are likely to engage with. This can influence users’ attitudes and cause confusion. Therefore, social media is a double-edged sword. Combating fake news and biased content has become one of the essential tasks. This research analyzes the variety of methods used for fake news detection covering random forest, logistic regression, support vector machines, decision tree, naive Bayes, BoW, TF-IDF, LDA, CNN, RNN, LSTM, DeepFake, and hierarchical attention network. The performance of each method is analyzed. Based on these models’ achievements and limitations, a multi-dimensional AI framework is proposed to achieve higher accuracy in infodemic detection, especially pandemic-related news. The model is trained on contextual content, images, and news metadata.

Keywords: artificial intelligence, fake news detection, infodemic detection, image recognition, sentiment analysis

Procedia PDF Downloads 205

Authors: Ankita Wadhawan, Parteek Kumar, Umesh Kumar

Abstract:

Gesture is any body movement that expresses some attitude or any sentiment. Gestures as a sign language are used by deaf people for conveying messages which helps in eliminating the communication barrier between deaf people and normal persons. Nowadays, everybody is using mobile phone and computer as a very important gadget in their life. But there are some physically challenged people who are blind/deaf and the use of mobile phone or computer like device is very difficult for them. So, there is an immense need of a system which works on body gesture or sign language as input. In this research, Microsoft Kinect Sensor, SDK V2 and Hidden Markov Toolkit (HTK) are used to recognize the object, motion of object and human body joints through Touch less NUI (Natural User Interface) in real-time. The depth data collected from Microsoft Kinect has been used to recognize gestures of Indian Sign Language (ISL). The recorded clips are analyzed using depth, IR and skeletal data at different angles and positions. The proposed system has an average accuracy of 85%. The developed Touch less NUI provides an interface to recognize gestures and controls the cursor and click operation in computer just by waving hand gesture. This research will help deaf people to make use of mobile phones, computers and socialize among other persons in the society.

Keywords: gesture recognition, Indian sign language, Microsoft Kinect, natural user interface, sign language

Procedia PDF Downloads 278

Authors: Kyung Bae Park, Sung Ho Ha

Abstract:

Online user-generated contents (UGC) significantly change the way customers behave (e.g., shop, travel), and a pressing need to handle the overwhelmingly plethora amount of various UGC is one of the paramount issues for management. However, a current approach (e.g., sentiment analysis) is often ineffective for leveraging textual information to detect the problems or issues that a certain management suffers from. In this paper, we employ text mining of Latent Dirichlet Allocation (LDA) on a popular online review site dedicated to complaint from users. We find that the employed LDA efficiently detects customer complaints, and a further inspection with the visualization technique is effective to categorize the problems or issues. As such, management can identify the issues at stake and prioritize them accordingly in a timely manner given the limited amount of resources. The findings provide managerial insights into how analytics on social media can help maintain and improve their reputation management. Our interdisciplinary approach also highlights several insights by applying machine learning techniques in marketing research domain. On a broader technical note, this paper illustrates the details of how to implement LDA in R program from a beginning (data collection in R) to an end (LDA analysis in R) since the instruction is still largely undocumented. In this regard, it will help lower the boundary for interdisciplinary researcher to conduct related research.

Keywords: latent dirichlet allocation, R program, text mining, topic model, user generated contents, visualization

Procedia PDF Downloads 160

Authors: Nidhal Mgadmi, Abdelhafidh Othmani

Abstract:

This article examines the causal relationship between stock indices and cryptocurrencies during the current war between Russia and Ukraine. The econometric investigation runs from February 24, 2022, to April 12, 2023, focusing on seven stock market indices (S&P500, DAX, CAC40, Nikkei, TSX, MOEX, and PFTS) and seven cryptocurrencies (Bitcoin, Ethereum, Litcoin, Dash, Ripple, DigiByte and XEM). In this article, we try to understand how investors react to fluctuations in financial assets to seek safe havens in cryptocurrencies. We used dynamic causality to detect a possible causal relationship in the short term and seven models to estimate the long-term relationship between cryptocurrencies and financial assets. The causal relationship between financial market indexes and cryptocurrency coins in the short run indicates that three famous cryptocurrencies (BITCOIN, ETHEREUM, RIPPLE) and the two digital assets with minor popularity (XEM, Digibyte) are impacted by the German, Russian, and Ukrainian stock markets. In the long run, we found a positive and significate effect of the American, Canadian, French, and Ukrainian stock market indexes on Bitcoin. Thus, the stability of the traditional financial markets during the current war period can be explained on the one hand by investors’ fears of an unstable business climate, and on the other hand, by speculators’ sentiment towards new electronic products, which are perceived as hedging instruments and a safe haven in the face of the conflict between Ukraine and Russia.

Keywords: causality, stock indices, cryptocurrency, war, Russia, Ukraine

Procedia PDF Downloads 41

Authors: Prajwal Eachempati, Laurent Muzellec, Ashish Kumar Jha

Abstract:

We use Facebook as a case study to investigate the complex relationship between the firm’s public discourse (and actions) surrounding data privacy and the performance of a business model based on monetizing user’s data. We do so by looking at the evolution of public discourse over time (2004–2021) and relate topics to revenue and stock market evolution Drawing from archival sources like Zuckerberg We use LDA topic modelling algorithm to reveal 19 topics regrouped in 6 major themes. We first show how, by using persuasive and convincing language that promises better protection of consumer data usage, but also emphasizes greater user control over their own data, the privacy issue is being reframed as one of greater user control and responsibility. Second, we aim to understand and put a value on the extent to which privacy disclosures have a potential impact on the financial performance of social media firms. There we found significant relationship between the topics pertaining to privacy and social media/technology, sentiment score and stock market prices. Revenue is found to be impacted by topics pertaining to politics and new product and service innovations while number of active users is not impacted by the topics unless moderated by external control variables like Return on Assets and Brand Equity.

Keywords: public discourses, data protection, social media, privacy, topic modeling, business models, financial performance

Procedia PDF Downloads 62

Authors: José Manue Carvalho Vieira, Mariana Magalhães, Elizabeth Serra

Abstract:

The Port Wine industry is essential to Portugal because it carries a tangible cultural heritage and for social and economic reasons. Positioned as a luxury product, brands need to pay more attention to the new generation's habits, preferences, languages, and sensory perceptions. Healthy lifestyles, anti-alcohol campaigns, and digitalisation of their buying decision process need to be better understood to understand the wine market in the future. The purpose of this study is to clarify the sensory perception gap between Port Wine descriptors promotion and the new generation's perceptions to help wineries to align their strategies. Based on the interpretivist approach - multiple methods and techniques (mixed-methods), different world views and different assumptions, and different data collection methods and analysis, this research integrated qualitative semi-structured interviews, Port Wine promotion contents, and social media perceptions mined by Sentiment Analysis Enginius algorithm. Findings confirm that Port Wine CEOs' strategies, brands' promotional content, and social perceptions are not sufficiently aligned. The central insight for Port Wine brands' managers is that there is a long and continuous work of understanding and associating their descriptors with the most relevant perceptual values and criteria of their targets to reposition (when necessary) and sustainably revitalise their brands. Finally, this study hypothesised a sensory gap that leads to a decrease in consumption, trying to find recommendations on how to transform it into an advantage for a better attraction towards the young age group (18-25).

Keywords: port wine, consumer habits, sensory gap analysis, wine marketing

Procedia PDF Downloads 203

Authors: Mohamed Lotfy, Ghada Soliman

Abstract:

Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes. This paper presents an approach for recognizing Arabic digits printed in dot matrix format. The proposed model is based on Convolutional Neural Networks (CNN) that take the dot matrix as input and generate embeddings that are rounded to generate binary representations of the digits. The binary embeddings are then used to perform Optical Character Recognition (OCR) on the digit images. To overcome the challenge of the limited availability of dotted Arabic expiration date images, we developed a True Type Font (TTF) for generating synthetic images of Arabic dot-matrix characters. The model was trained on a synthetic dataset of 3287 images and 658 synthetic images for testing, representing realistic expiration dates from 2019 to 2027 in the format of yyyy/mm/dd. Our model achieved an accuracy of 98.94% on the expiry date recognition with Arabic dot matrix format using fewer parameters and less computational resources than traditional CNN-based models. By investigating and presenting our findings comprehensively, we aim to contribute substantially to the field of OCR and pave the way for advancements in Arabic dot-matrix character recognition. Our proposed approach is not limited to Arabic dot matrix digit recognition but can also be extended to text recognition tasks, such as text classification and sentiment analysis.

Keywords: computer vision, pattern recognition, optical character recognition, deep learning

Procedia PDF Downloads 50

Authors: Frederick Kobe O. Obar, Preity B. Quinzon, Trisha B. Tumbokon, Mario Joshua D. Marron, Kenichi Katsuo Kichiro A. Rimorin

Abstract:

The Public Utility Vehicle Modernization Program (PUVMP) is a program meant to reform the current state of the Philippines’ public transportation sector. This study determined the impact of the Public Utility Vehicle Modernization Program on San Fernando City, La Union's jeepney drivers, interviewing six individuals, three with traditional vehicles and three with modernized units. This study used a descriptive qualitative research design and employed purposive sampling to select the six participants suited for the study, who were then subjected to a semi-structured face-to-face interview. The gathered data was then analyzed through thematic analysis. The findings highlighted evidence that the jeepney drivers experienced abrupt and prevailing changes in their routine and in their everyday work. This study concludes that while the sentiment of the program was appreciated, it has changed the environment for jeepney drivers drastically, provoking many reactions. These changes have, of course, shifted the daily lives of the jeepney drivers significantly, but through adaptability, they found ways. Recommendations include flexible compliance policies, educational initiatives, and support for drivers, providing valuable insights for informed decision-making in the ongoing transportation modernization discussion. This study concluded that while the drivers are not opposed to reform, they are not entirely in approval of the current effects of the program as it is being implemented in their local area.

Keywords: transport reform, transport modernization, public transport, jeepney drivers, PUVMP, urban planning, public utility vehicles

Procedia PDF Downloads 26

Authors: Zicheng Zhang, Linli Zhang

Abstract:

As China's biggest social media platform, Weibo has taken on essential health communication responsibilities during the pandemic. This research takes 105 posters in 15 health-related official Weibo accounts as the analysis objects to explore COVID19 health information communication and visualisation. First, the interaction between the audiences and Weibo, including forwarding, comments, and likes, is statistically analysed. The comments about the information design are extracted manually, and then the sentiment analysis is carried out to verdict audiences' views about the poster's design. The forwarding and comments are quantified as the attention index for a reference to the degree of likes. In addition, this study also designed an evaluation scale based on the standards of Health Literacy Resource by the Centers for Medicare& Medicaid Services (US). Then designers scored all selected posters one by one. Finally, combining the data of the two parts, concluded that: 1. To a certain extent, people think that the posters do not deliver substantive and practical information; 2. Non-knowledge posters(i.e., cartoon posters) gained more Forwarding and Likes, such as Go, Wuhan poster; 3. The analysis of COVID posters is still mainly picture-oriented, mainly about encouraging people to overcome difficulties; 4. Posters for pandemic prevention usually contain more text and fewer illustrations and do not clearly show cultural differences. In conclusion, health communication usually involves a lot of professional knowledge, so visualising that knowledge in an accessible way for the general public is challenging. The relevant posters still have the problems of lack of effective communication, superficial design, and insufficient content accessibility.

Keywords: weibo, visualisation, covid posters, poster design

Procedia PDF Downloads 93

Authors: Sarah Marie

Abstract:

In today's dynamic financial landscape, cryptocurrencies represent a paradigm shift characterized by innovation and intense debate. This study probes into their transformative potential and the challenges they present, offering a balanced perspective that recognizes both their promise and pitfalls. Emulating the engaging style of a TED Talk, this research goes beyond academic analysis, serving as a critical bridge to reconcile the perspectives of cryptocurrency skeptics and enthusiasts, fostering a well-informed dialogue. The study employs a mixed-method approach, analyzing current trends, regulatory landscapes, and public perceptions in the cryptocurrency domain. It distinguishes genuine innovators in this field from ostentatious opportunists, echoing the sentiment that real innovation should be separated from mere showmanship. If one is unfamiliar with who is being referenced, they can likely spot them leaning against their Lamborghinis outside "Crypto" conventions, looking greasy. Major findings reveal a complex scenario dominated by regulatory uncertainties, market volatility, and security issues, emphasizing the need for a coherent regulatory framework that balances innovation with risk management and sustainable practices. The study underscores the importance of transparency and consumer protection in fostering responsible growth within the cryptocurrency ecosystem. In conclusion, the research advocates for education, innovation, and ethical governance in the realm of cryptocurrencies. It calls for collaborative efforts to navigate the intricacies of this evolving landscape and to realize its full potential in a responsible, inclusive, and forward-thinking manner.

Keywords: financial landscape, innovation, public perception, transparency

Procedia PDF Downloads 15

Authors: Raymond Xu, Ashley Hua, Andrew Wang, Yuru Lin

Abstract:

During COVID-19, the depression rate has increased dramatically. Young adults are most vulnerable to the mental health effects of the pandemic. Lower-income families have a higher ratio to be diagnosed with depression than the general population, but less access to clinics. This research aims to achieve early depression detection at low cost, large scale, and high accuracy with an interdisciplinary approach by incorporating clinical practices defined by American Psychiatric Association (APA) as well as multimodal AI framework. The proposed approach detected the nine depression symptoms with Natural Language Processing sentiment analysis and a symptom-based Lexicon uniquely designed for young adults. The experiments were conducted on the multimedia survey results from adolescents and young adults and unbiased Twitter communications. The result was further aggregated with the facial emotional cues analyzed by the Convolutional Neural Network on the multimedia survey videos. Five experiments each conducted on 10k data entries reached consistent results with an average accuracy of 88.31%, higher than the existing natural language analysis models. This approach can reach 300+ million daily active Twitter users and is highly accessible by low-income populations to promote early depression detection to raise awareness in adolescents and young adults and reveal complementary cues to assist clinical depression diagnosis.

Keywords: artificial intelligence, COVID-19, depression detection, psychiatric disorder

Procedia PDF Downloads 101

Authors: Vasanth Narayanan

Abstract:

The mid-nineteenth century saw the Japanese elite and townsfolk alike undergo the now-infamous Ansei Edo earthquakes. The quakes decimated Japan in the final decades of the Tokugawa Era and, perhaps more consequentially, birthed a new genre of politically inspired artwork, the most notable of which are the namazu-e. This essay advocates an understanding of the 1855 Catfish Prints (namazu-e) that prioritizes the function of iconography and anthropomorphic deity in shaping the namazu-e into a wholly political experience that makes the censorship of the time part of its argument. The visual program is defined as the creation of a politically profitable experience, crafted through the union of explicit religion, highly masked commentary, and the impositions of censorship. The strategies by which the works are designed, in the face of censorship, to engage a less educated, pedestrian audience with its theme, including considerations of iconography, depictions of the working class, anthropomorphism, and the relationship between textual and visual elements, are discussed herein. The essay then takes up the question of the role of tense Japan–United States relations in fostering censorship and as a driver of the production of namazu-e. It is ultimately understood that the marriage of hefty censorship protocol, the explicitly religious medium, and inimical sentiment towards United States efforts at diplomacy renders the production of namazu-e an offspring of the censorship and deeply held frustrations of the time, cementing its status as a primitive form of peaceful protest against a seemingly apathetic government.

Keywords: Japan, Ansei Earthquake, Namazu, prints, censorship, religion

Procedia PDF Downloads 85

Authors: Patricia Portugal Marques de Carvalho Lourenco

Abstract:

Big Bang is like a dirty martini embroiled in a stew of personal individual scandals that have rocked the group’s image and perception, from G-Dragon’s and T.O.P. marijuana episodes in 2011 and 2016, respectively, to Daesung’s building illicit entertainment activities in 2018to the Burning Sun shebang that led to the Titanic sink of Big Bang’s youngest member Seungri in 2019 and the positive sentiment migration to the antithetical side. BTS, on the other hand, are like a martini, clear, clean, attracting as many crowds to their performances and online content as the Pope attracts believers to Sunday Mass in the Vatican, as exemplified by their latest MVs. Big Bang’s 2022 Still Life achieved 16.4 million views on Youtube in 24hours, whilst BTS Permission to Dance achieved 68.5 million in the same period of time. The difference is significant when added Big Bang’s and BTS overall award wins, a total of 117 in contrast to 460. Both groups are uniquely talented and exceptional performers that have been contributing greatly to the dissemination of Korean Pop Music on a global scale in their own inimitable ways. Both are exceptional in their own right and while the artists cannot, ought not, should not be compared for the grave injustice made in comparing one individual planet with one solar system, a contrast is merited and hence done. The reality, nonetheless, is about disengagement from a group that lives life humanly, learning and evolving with each challenge and mistake without a clean, perfect tag attached to it, demonstrating not only an inability to disassociate the person from the artist and the music but also an inability to understand the difference between a private and public life.

Keywords: K-Pop, big bang, BTS, music, public image, entertainment, korean entertainment

Procedia PDF Downloads 72

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: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: deep learning, data mining, gender predication, MOOCs

Procedia PDF Downloads 114