Review
Computer Science, Artificial Intelligence
Francisca Adoma Acheampong, Henry Nunoo-Mensah, Wenyu Chen
Summary: The importance of contextual information in NLP applications cannot be emphasized enough, with significant improvements observed in tasks like emotion recognition from texts. This paper discusses transformer-based models for NLP tasks, highlighting the pros and cons of models such as GPT, Transformer-XL, XLM, and BERT. Researchers have proposed various BERT-based models for text-based emotion detection due to BERT's strength and popularity in this field.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Review
Chemistry, Multidisciplinary
Yili Wang, Jiaxuan Guo, Chengsheng Yuan, Baozhu Li
Summary: Twitter Sentiment Analysis is an active subfield of text mining, which has attracted considerable interest among researchers. This research provides a comprehensive review of the latest developments in this area, including newly proposed algorithms and applications. The survey classifies each publication based on its significance to specific TSA methods and depicts the current research direction in the field of TSA.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Monali Bordoloi, Saroj Kumar Biswas
Summary: Sentiment analysis is a solution for extracting summarized opinions or details from a large data source. A thorough analysis of the process for developing an efficient sentiment analysis model is desired. Factors such as word extraction, sentiment classification, dataset, and data cleansing greatly affect the performance of a sentiment analysis model. This paper provides in-depth knowledge of different techniques, algorithms, and factors associated with designing effective sentiment analysis models. It also critically assesses different modules of a sentiment analysis framework, discusses shortcomings of existing methods, and proposes potential multidisciplinary applications and research directions.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Kazuyuki Matsumoto, Manabu Sasayama, Minoru Yoshida, Kenji Kita, Fuji Ren
Summary: Dialogue breakdown analysis is crucial for improving chat dialogues. Conventional methods focusing on semantic variance may fail to detect emotional breakdowns. This study proposes a method that analyzes emotional changes to detect dialogue breakdowns.
Article
Computer Science, Artificial Intelligence
Jing Li, Billy Chiu, Shuo Shang, Ling Shao
Summary: This paper discusses the importance of text segmentation and the limitations of traditional solutions. It proposes the SEGBOT model, an end-to-end segmentation model that uses neural networks to address the issues of variable size output vocabulary and sparse boundary tags. The results of this model are then applied to sentence-level sentiment analysis, achieving state-of-the-art results.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Sergio Barreto, Ricardo Moura, Jonnathan Carvalho, Aline Paes, Alexandre Plastino
Summary: With the rapid growth of social media networks, user-generated data on platforms like Twitter has become a valuable resource for decision-making processes. However, the informal and noisy linguistic style of tweets poses challenges for natural language processing tasks, especially sentiment analysis. This study assesses the effectiveness of various neural language models in distinguishing sentiment expressed in tweets.
DATA MINING AND KNOWLEDGE DISCOVERY
(2023)
Article
Computer Science, Information Systems
Alejandro De Leon Langure, Mahdi Zareei
Summary: Sentiment analysis and text emotion detection are computer techniques used to analyze text and identify human emotions. However, most research focuses on comparing computational methods, while less attention is paid to selecting emotion models, training corpora, and data sources. The lack of standardization in these critical factors presents a challenge for meaningful performance comparisons among algorithms.
Article
Computer Science, Information Systems
Gildasio Antonio de Oliveira Junior, Rafael Timoteo de Sousa Jr, Robson de Oliveira Albuquerque, Luis Javier Garcia Villalba
Summary: This research focuses on the robustness and vulnerabilities of sentiment classifiers in social media applications against new adversarial attacks, proposing some countermeasures that might mitigate these attacks.
COMPUTER COMMUNICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Rehab Duwairi, Ftoon Abushaqra
Summary: Arabic language poses challenges for automatic processing due to its characteristics, which results in scarce high-quality datasets. However, this study innovatively introduces an intelligent framework for expanding Arabic text, achieving high accuracy gains.
PEERJ COMPUTER SCIENCE
(2021)
Review
Computer Science, Information Systems
Satarupa Biswas, G. Poornalatha
Summary: This paper addresses the emerging literature in Opinion Mining, focusing on user-generated textual content. It discusses the various tasks involved in Opinion Mining, providing insights into the essential criteria and methodologies. The paper also analyzes benchmarked datasets, feature sets, algorithms, techniques, open-source tools, challenges, real-world applications, and dimensions of Opinion Mining. The findings highlight the theoretical and practical implications of Opinion Mining in comprehending textual content in society. The review provides both technical and real-world knowledge, offering a comprehensive understanding of available open-source tools for real-time use.
Article
Computer Science, Artificial Intelligence
Hanyun Li, Wenzao Li, Jiacheng Zhao, Peizhen Yu, Yao Huang
Summary: Using technology for sentiment analysis in the travel industry is valuable for understanding customers' emotions and improving service quality. However, travel-related online reviews often have linguistic challenges, making traditional methods inaccurate. To address this, a dual-channel algorithm integrating CNN and BiLSTM with attention mechanism (DC-CBLA) is proposed, achieving high accuracy in classifying tourist reviews.
PEERJ COMPUTER SCIENCE
(2023)
Article
Food Science & Technology
Ziyang Chen, Cristhiam Gurdian, Chetan Sharma, Witoon Prinyawiwatkul, Damir D. Torrico
Summary: Increased meat consumption has been linked to various environmental and animal welfare issues. To address this, alternative proteins like plant-based and insect-based proteins have gained popularity in research. Text mining and NLP have been explored as efficient tools in identifying trends and sentiments in sensory studies, providing a rapid and comprehensive analysis of consumer perceptions towards alternative proteins.
Article
Public, Environmental & Occupational Health
Chenjing Fan, Zhenyu Gai, Shiqi Li, Yirui Cao, Yueying Gu, Chenxi Jin, Yiyang Zhang, Yanling Ge, Lin Zhou
Summary: This study used 147,613 Weibo text check-ins in Xiamen to quantify residents' sentiments in 1,096 neighborhoods. The results showed that neighborhoods with high land value, low plot ratio, low population density, and proximity to water were more likely to improve residents' sentiments. At the subdistrict level, more green space and commercial land, less industry, higher building and road density, and a smaller migrant population were associated with positive sentiments. These findings provide data support for urban planning and improving residents' living environment.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Computer Science, Artificial Intelligence
Anandan Chinnalagu, Ashok Kumar Durairaj
Summary: Researchers have tackled the challenge of analyzing customer sentiment in reviews using various algorithms and models, while also revealing issues of performance and cost. This experiment developed a high-performance and cost-effective model to predict accurate sentiments from large datasets containing customer reviews.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Bo Xu, Hongfei Lin, Yuan Lin, Kan Xu
Summary: Textual emotion analysis is a challenging research topic in NLP, with recent focus on fine-grained emotion analysis to probe the essential elements of emotions. This paper proposes a two-stage supervised ranking method for accurately extracting emotion causes, which significantly outperforms state-of-the-art baseline methods in emotion cause extraction tasks. The proposed method effectively extracts textual emotion causes in sentences, benefiting in-depth emotion analysis for effective cognitive computing.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Kivanc Tatar, Philippe Pasquier
JOURNAL OF NEW MUSIC RESEARCH
(2019)
Article
Computer Science, Interdisciplinary Applications
Miles Thorogood, Jianyu Fan, Philippe Pasquier
JOURNAL OF NEW MUSIC RESEARCH
(2019)
Article
Multidisciplinary Sciences
Ulysses Bernardet, Sarah Fdili Alaoui, Karen Studd, Karen Bradley, Philippe Pasquier, Thecla Schiphorst
Article
Computer Science, Cybernetics
Cale Plut, Philippe Pasquier
ENTERTAINMENT COMPUTING
(2020)
Article
Computer Science, Artificial Intelligence
Kivanc Tatar, Daniel Bisig, Philippe Pasquier
Summary: The research introduces a new audio synthesis method called Latent Timbre Synthesis, which uses deep learning to interpolate and extrapolate between the timbre of multiple sounds in the latent space of audio frames. It compares two Variational Autoencoder architectures and provides an open-source application for practitioners to generate timbres.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Education & Educational Research
Zoran Sevarac, Jelena Jovanovic, Vladan Devedzic, Bojan Tomic
Summary: The EXPLODE model is a new exploratory learning environment for teaching and learning neural networks. It transforms a software development environment into a pedagogically instrumented space, aimed at improving students' learning outcomes and experiences. The model was evaluated in an experimental study with positive results.
INTERACTIVE LEARNING ENVIRONMENTS
(2022)
Proceedings Paper
Computer Science, Cybernetics
Mirjana Prpa, Sarah Fdili-Aloui, Thecla Schiphorst, Philippe Pasquier
PROCEEDINGS OF THE 2020 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI'20)
(2020)
Proceedings Paper
Acoustics
Jianyu Fan, Yi-Hsuan Yang, Kui Dong, Philippe Pasquier
2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
(2020)
Proceedings Paper
Acoustics
Jianyu Fan, Eric Nichols, Daniel Tompkins, Ana Elisa Mendez-Mendez, Benjamin Elizalde, Philippe Pasquier
2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING
(2020)
Article
Engineering, Electrical & Electronic
Vladan Devedzic
FACTA UNIVERSITATIS-SERIES ELECTRONICS AND ENERGETICS
(2020)
Article
Music
Kivanc Tatar, Mirjana Prpa, Philippe Pasquier
LEONARDO MUSIC JOURNAL
(2019)
Proceedings Paper
Computer Science, Cybernetics
John Desnoyers-Stewart, Ekaterina R. Stepanova, Philippe Pasquier, Bernhard E. Riecke
CHI EA '19 EXTENDED ABSTRACTS: EXTENDED ABSTRACTS OF THE 2019 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS
(2019)
Proceedings Paper
Computer Science, Cybernetics
Min Fan, Jianyu Fan, Alissa N. Antle, Sheng Jin, Dongxu Yin, Philippe Pasquier
CHI EA '19 EXTENDED ABSTRACTS: EXTENDED ABSTRACTS OF THE 2019 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS
(2019)
Article
Education & Educational Research
Bojan Tomic, Jelena Jovanovic, Nikola Milikic, Vladan Devedzic, Sonja Dimitrijevic, Dragan Duric, Zoran Sevarac
BRITISH JOURNAL OF EDUCATIONAL TECHNOLOGY
(2019)
Proceedings Paper
Engineering, Biomedical
G. Devedzic, S. Petrovic, A. Matic, B. Ristic, V. Devedzic, Z. Asgharpour, S. Cukovic
