Article
Psychology, Multidisciplinary
Lichun Zhou
Summary: This paper investigates the quantitative model of brand recognition based on sentiment analysis of big data using laptops as an example. Through web crawler technology, the most authentic information about different laptop brands is collected from first-line consumers on major e-commerce platforms. The study analyzes consumers' sentiment and recognition of product brands by analyzing review time, text reviews, satisfaction ratings, and relevant user information. The results show that the quantitative model can transform keywords in text into word vectors in high-dimensional semantic space through unsupervised machine learning, and accumulate values in each dimension of brand recognition to obtain the overall value of each brand recognition.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Information Systems
Ranjan Kumar Behera, Monalisa Jena, Santanu Kumar Rath, Sanjay Misra
Summary: The study proposes a hybrid approach using Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) for sentiment classification of consumer reviews posted in social media. The experimental results show that the proposed ensemble model outperforms other machine learning approaches in terms of accuracy and other parameters.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Psychology, Multidisciplinary
Zhu Yuan
Summary: This paper proposes a method to analyze the value of online travel reviews using big data and machine learning technology. By pre-processing travel review texts and improving the SVM algorithm, combined with Hadoop Distributed File System, fast and accurate travel sentiment classification is achieved.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Theory & Methods
Ringki Das, Thoudam Doren Singh
Summary: Sentiment analysis has evolved from unimodality to multimodality, incorporating text, audio, and video data. Complex deep neural network architectures, such as transformer-based models, have shown significant success in improving sentiment analysis performance. This comprehensive study highlights the changing trends in sentiment analysis and emphasizes its tremendous potential.
ACM COMPUTING SURVEYS
(2023)
Article
Mathematical & Computational Biology
Chen Xi
Summary: This paper studies the influencing factors of music emotion expression, proposes an analysis model based on the PSO-BP neural network, and verifies its effectiveness through multiple experiments.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2021)
Article
Computer Science, Information Systems
Jang Hyun Kim, Dongyan Nan, Yerin Kim, Hyung Park Min
Summary: The study utilizes a big data approach to investigate user satisfaction among Uber users and finds that hedonic, promotion, and pragmatic elements significantly positively impact user satisfaction, while burden, cost, and risk have substantial negative effects. Anger plays a more crucial role in increasing perceived burden for users compared to sadness and anxiety.
CMC-COMPUTERS MATERIALS & CONTINUA
(2021)
Article
Business, Finance
Gopal K. Basak, Pranab Kumar Das, Sugata Marjit, Debashis Mukherjee, Lei Yang
Summary: In this study, we utilize a machine learning framework and analyze a large collection of media articles on Brexit to provide evidence of cointegration and causality between the sentiments of the media and the movement of British currency. Our contribution is unique as we not only use common sentiment analysis lexicons, but also develop a Bayesian learning-based method to construct a more context-aware and informative lexicon specifically for Brexit. By leveraging and expanding on this method, we uncover the relationship between original media sentiment and related economic and financial variables. Our approach outperforms conventional ones in terms of predicting out-of-sample outcomes.
NORTH AMERICAN JOURNAL OF ECONOMICS AND FINANCE
(2023)
Article
Computer Science, Information Systems
Fang Qiao, Jago Williams
Summary: This study examines the topics and sentiments of global warming discussion on Twitter using big data analytics techniques. It identifies seven main topics frequently debated, including factors causing global warming, consequences of global warming, actions necessary to stop global warming, and other related issues. The sentiment analysis reveals that most people express positive emotions about global warming, with fear being the most evoked emotion.
JOURNAL OF ORGANIZATIONAL AND END USER COMPUTING
(2022)
Article
Chemistry, Multidisciplinary
Laura Gabriela Tanasescu, Andreea Vines, Ana Ramona Bologa, Claudia Antal Vaida
Summary: This paper discusses the challenges of applying big data analysis in the human resource sector and explores how employee review data can be utilized for business decision adjustment and changes. Experimental results demonstrate that logistic regression performs better in predicting employee sentiment.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Sergey Smetanin
Summary: This article presents RuSentiTweet, a sentiment analysis dataset of general domain tweets in Russian, which is currently the largest in its class. It consists of 13,392 manually annotated tweets and is divided into five classes. Additionally, a RuBERT-based sentiment classification model is released.
PEERJ COMPUTER SCIENCE
(2022)
Article
Multidisciplinary Sciences
Manuel Cebral-Loureda, Alberto Hernandez-Baqueiro, Enrique Tames-Munoz
Summary: The power of social media to spread the idea of wellbeing has been studied by psychologists and scholars, but the use of the human flourishing concept in these platforms remains unexplored. This study analyzes over 600 thousand Twitter messages from users associating themselves with human flourishing, comparing them to messages from other Twitter lists. The study aims to identify HF users' interests, vocabulary richness, shared emotions, and grammar usage. Text mining methods including sentiment analysis, natural language processing, and topic modeling were employed. The results show that although HF users exhibit average vocabulary diversity, they share more positive emotions and use a greater variety of emojis. Their discussions cover spiritual, health-related, and practical subjects such as work and success. They also display empathy, caring about people's daily emotions and the world.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Theory & Methods
Kashif Ali, Margaret Hamilton, Charles Thevathayan, Xiuzhen Zhang
Summary: Social media provides an infrastructure for fast data sharing without worrying about storage and processing. However, existing social media data analysis tools lack flexibility in processing and analyzing data due to their uniform treatment of different data sources. To address this issue, we developed a framework that extracts and transforms data from various social media platforms, capturing the dynamic features of social media data and composing appropriate services for information analysis.
JOURNAL OF BIG DATA
(2022)
Article
Chemistry, Multidisciplinary
Qizhi Li, Xianyong Li, Yajun Du, Yongquan Fan, Xiaoliang Chen
Summary: This paper proposes a new sentiment-enhanced word embedding method to improve sentence-level sentiment classification. By leveraging the mapping relationship between word embeddings and sentiment orientations, the method achieves higher accuracy and F1 values and reduces convergence time in sentiment classification models.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Kia Dashtipour, Mandar Gogate, Erik Cambria, Amir Hussain
Summary: Recent studies show that utilizing multimodal data can effectively gauge public perception, and a Persian multimodal dataset and sentiment analysis framework are provided as research resources. Experimental results demonstrate that integrating multimodal features can enhance sentiment analysis performance.
Article
Computer Science, Artificial Intelligence
Swasthika Jain Thandaga Jwalanaiah, Israel Jeena Jacob, Ajay Kumar Mandava
Summary: As images, memes, and graphics interchange formats have become more popular on social media, typographic/infographic visual content has emerged as a critical component. This article presents a deep learning-based multimodal sentiment analysis model that effectively analyzes visual and textual content to determine sentiment. The proposed method achieves high accuracy in sentiment analysis of text, visual content, and multimodal text compared to other methods.
Article
Computer Science, Artificial Intelligence
Mohammad AL-Smadi, Mahmoud M. Hammad, Sa'ad A. Al-Zboon, Saja AL-Tawalbeh, Erik Cambria
Summary: The increasing interactive content in the Internet has led to research on Aspect-Based Sentiment Analysis (ABSA) in order to understand sentiments and aspects of a product in user comments. A deep learning model based on Gated Recurrent Units (GRU) and features extracted using the Multilingual Universal Sentence Encoder (MUSE) was developed for aspect extraction and polarity classification. The proposed Pooled-GRU model achieved high F1 scores of 93.0% for aspect extraction and 90.86% for aspect polarity classification, outperforming the baseline model and related research methods.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Siddique Latif, Heriberto Cuayahuitl, Farrukh Pervez, Fahad Shamshad, Hafiz Shehbaz Ali, Erik Cambria
Summary: This article provides a comprehensive survey on the progress of deep reinforcement learning (DRL) in the audio domain. By examining research studies in areas such as speech and music, the article discusses the methods and applications of DRL, and highlights the challenges and open areas for future research in the audio domain.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Nushrat Khan, Mike Thelwall, Kayvan Kousha
Summary: This study investigates differences and commonalities in data production, sharing, and reuse across various academic disciplines. The findings suggest that data sharing and reuse are increasing but not widespread in any subject area, and experienced researchers are more likely to engage in these practices. The types of data produced and the methods of sharing vary significantly between disciplines. Researchers' feedback provided recommendations for improving data access, usability, and awareness of data sharing and reuse.
ONLINE INFORMATION REVIEW
(2023)
Article
Computer Science, Artificial Intelligence
Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria
Summary: We propose a heterogeneous graph attention network to address the problem of dialogue relation extraction. Compared with several popular sequence-based and graph-based models, our method shows superior performance on the benchmark dataset DialogRE.
COGNITIVE COMPUTATION
(2023)
Article
Chemistry, Multidisciplinary
Atnafu Lambebo Tonja, Olga Kolesnikova, Alexander Gelbukh, Grigori Sidorov
Summary: This paper discusses the feasibility of using source-side monolingual dataset of low-resource languages to improve the NMT system. Experiments show that both self-learning and fine-tuning approaches can enhance the translation quality for low-resource Wolaytta-English translation.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Iqra Ameer, Necva Bolucu, Muhammad Hammad Fahim Siddiqui, Burcu Can, Grigori Sidorov, Alexander Gelbukh
Summary: Social media is a valuable platform for understanding people's emotions. The use of multiple attention mechanisms and Transformer networks has been shown to improve accuracy in emotion classification.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jintao Wen, Dazhi Jiang, Geng Tu, Cheng Liu, Erik Cambria
Summary: Multimodal data is crucial for enhanced emotion recognition in conversation, but effectively fusing different modal features to understand contextual information is challenging. This work proposes a Dynamic Interactive Multiview Memory Network (DIMMN) model, which integrates interaction information and mines crossmodal dynamic dependencies for emotion recognition. Experimental results show that DIMMN achieves better performance compared to state-of-the-art methods.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Yu Ma, Rui Mao, Qika Lin, Peng Wu, Erik Cambria
Summary: This study proposes a novel Multi-source Aggregated Classification (MAC) method for predicting stock price movements. MAC incorporates numerical features, market-driven news sentiments, and sentiments of related stocks to better represent real market sentiments. The method also utilizes a graph convolutional network to capture the effects of news from related companies on the target stock. Extensive experiments demonstrate that MAC outperforms state-of-the-art models in predicting stock price movements, Sharpe Ratio, and backtesting trading incomes.
INFORMATION FUSION
(2023)
Article
Computer Science, Information Systems
Qian Liu, Rui Mao, Xiubo Geng, Erik Cambria
Summary: This paper conducts a systematic empirical study on semantic matching in machine reading comprehension (MRC). It formulates a two-stage framework and compares different setups of semantic matching modules on four MRC datasets. The study finds that semantic matching improves the effectiveness and efficiency of MRC, especially for answering questions with noisy and adversarial context. Matching coarse-grained context to questions and using semantic matching modules is more effective than fine-grained context matching, such as sentences and spans. However, semantic matching decreases the performance on why questions, suggesting that it is more helpful for questions that can be answered by retrieving information from a single sentence.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Mike Thelwall, Kayvan Kousha, Mahshid Abdoli, Emma Stuart, Meiko Makita, Paul Wilson, Jonathan Levitt
Summary: Collaboration is believed to improve academic research, as indicated by more cited coauthored articles. However, this may be due to increased self-citations or the audience effect. The first science wide investigation using expert peer quality judgments for 122,331 articles from the UK national assessment shows moderately strong positive associations between author numbers and quality scores in the health, life, and physical sciences, weak or no positive associations in engineering and social sciences, and various associations in arts and humanities.
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Mike Thelwall, Kayvan Kousha, Mahshid Abdoli, Emma Stuart, Meiko Makita, Paul Wilson, Jonathan Levitt
Summary: This article reports the first assessment of the extent to which mature altmetrics from Mendeley associate with individual article quality scores. The study found that altmetrics are more strongly correlated with research quality than previously thought. Mendeley reader counts are the best altmetric indicator, followed by tweet counts.
JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Grigori Sidorov, Fazlourrahman Balouchzahi, Sabur Butt, Alexander Gelbukh
Summary: In this paper, the performance of different transformer models for regret and hope speech detection on two novel datasets was analyzed. The transformer models were found to outperform previous approaches in regret detection, with the roberta-based model achieving the highest macro F1-score of 0.83. For hope speech detection, the bert-based, uncased model achieved the highest macro F1-score of 0.72. However, the performance of each model varied slightly depending on the task and dataset. These findings emphasize the effectiveness of transformer models for hope speech and regret detection tasks, and the importance of considering context, specific transformer architectures, and pre-training on their performance.
APPLIED SCIENCES-BASEL
(2023)
Article
Education & Educational Research
Iti Chaturvedi, Erik Cambria, Roy E. Welsch
Summary: Video conferencing enables synchronous communication in classrooms and stimulates learners with multi-sensory content. Constructive pedagogy is used to teach complex AI equations, allowing students to experiment with different problem-solving methods. Multiple-choice questions provide reliable and quick assessments of student skill levels. The Australian Computer Society accreditation ensures flexible teaching templates for each subject. Geographic constraints necessitate subordinate campuses to be affiliated with a main campus. Continuity in learning and assessments between different subjects is maintained through the concept of strands. Feedback from students using AI-based simulations showed challenges in understanding lectures and assignments, hence a Kahoot quiz was introduced to measure learning. Charts were used to aid students with vision or attention-related disorders in visually observing variables and analyzing in-depth. Real-world industry examples were incorporated into lectures to enhance employability.
EDUCATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Rui Mao, Qian Liu, Kai He, Wei Li, Erik Cambria
Summary: With the breakthrough of large-scale pre-trained language model (PLM) technology, prompt-based classification tasks, such as sentiment analysis and emotion detection, have gained increasing attention. This study conducts a systematic empirical study on prompt-based sentiment analysis and emotion detection to investigate the biases of PLMs in affective computing.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)