Article
Computer Science, Artificial Intelligence
Yang Zhao, Tommy W. S. Chow
Summary: With the prosperity of online social media, there has been a significant increase in user-generated reviews. This paper introduces a sentiment subset selection framework to filter irrelevant sentiment information and select subsets based on topic modeling and submodular maximization with a cardinality constraint. Empirical analysis shows that the proposed framework can compress sentiment corpus while maintaining classifier performance on different metrics.
NEURAL COMPUTING & APPLICATIONS
(2021)
Review
Computer Science, Information Systems
Yuehua Zhao, Linyi Zhang, Chenxi Zeng, Wenrui Lu, Yidan Chen, Tao Fan
Summary: This study utilizes a double-layer domain ontology for aspect-level sentiment analysis of online medical reviews. A double-layer aspect recognition model is built, and an object-aspect-sentiment knowledge graph is constructed, providing reference and guidance to sentiment analysis research in the online medical review domain.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Business
Chia-Hsuan Chang, San-Yih Hwang, Ming-Lun Wu
Summary: High-quality sentiment lexicons are crucial for lexicon-based sentiment analysis, but most lexicons are only available in certain dominant languages, limiting their applicability in specific domains or languages. This paper proposes a multistep approach for bilingual sentiment lexicon induction to disambiguate words with opposite sentiment polarities, which outperforms existing lexicons and competing approaches in terms of accuracy and coverage, using experiments on real-world online review data sets.
ELECTRONIC COMMERCE RESEARCH AND APPLICATIONS
(2021)
Article
Chemistry, Multidisciplinary
Mengsheng Wang, Hailong You, Hongbin Ma, Xianhe Sun, Zhiqiang Wang
Summary: Massive online reviews of new energy vehicles in China are crucial for companies to gain valuable insights into user demands and perceptions. An enhanced hybrid model, combining ERNIE and deep CNN, is introduced to effectively analyze these reviews and adapt products while upholding a positive public image.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Guoshuai Zhao, Yiling Luo, Qiang Chen, Xueming Qian
Summary: This article presents a multitask learning model that combines ATE and APC tasks to extract aspect terms and classify aspect polarity simultaneously. It also utilizes multihead attention (MHA) to associate dependency sequences with aspect extraction, focusing on closely related words to aspects.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Psychology, Biological
Claire E. Robertson, Nicolas Proellochs, Kaoru Schwarzenegger, Philip Parnamets, Jay J. Van Bavel, Stefan Feuerriegel
Summary: Online media plays a crucial role in society, and understanding the factors that drive online news consumption is important. In this study, we examined the causal effect of negative and emotional words on news consumption using a large dataset of viral news stories. Our analysis, based on randomized controlled trials with over 22,743 participants, showed that the presence of negative words in news headlines increased consumption rates, while positive words decreased consumption rates. Each additional negative word in an average-length headline led to a 2.3% increase in click-through rates. These findings contribute to a better understanding of user engagement with online media.
NATURE HUMAN BEHAVIOUR
(2023)
Article
Computer Science, Information Systems
Yuming Lin, Yu Fu, You Li, Guoyong Cai, Aoying Zhou
Summary: This paper proposes a hybrid attention model for aspect-based sentiment analysis, utilizing self-attention mechanism and aspect-attention mechanism to generate semantic representation, and exploring auxiliary features of word location and part-of-speech. Experimental results demonstrate the advantage of the proposed model in both efficiency and execution effectiveness.
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Andrea Fronzetti Colladon, Francesca Grippa, Barbara Guardabascio, Gabriele Costante, Francesco Ravazzolo
Summary: This research examines the influence of online news on social and economic consumer perceptions through semantic network analysis. By analyzing over 1.8 million online articles from Italian media, the study finds that the words appearing in the articles can predict consumer judgments about the economic situation and the Consumer Confidence Index, offering a complementary approach to estimating consumer confidence.
SCIENTIFIC REPORTS
(2023)
Review
Computer Science, Artificial Intelligence
Ping Wang, Jiangnan Li, Jingrui Hou
Summary: This paper proposes a sentence-to-sentence attention network (S2SAN) using multihead self-attention for sentiment analysis, which outperforms other state-of-the-art models. By modeling attention at the sentence level, it enhances the accuracy of sentiment classifiers.
DECISION SUPPORT SYSTEMS
(2021)
Review
Computer Science, Artificial Intelligence
Iqra Safder, Zainab Mehmood, Raheem Sarwar, Saeed-Ul Hassan, Farooq Zaman, Rao Muhammad Adeel Nawab, Faisal Bukhari, Rabeeh Ayaz Abbasi, Salem Alelyani, Naif Radi Aljohani, Raheel Nawaz
Summary: This study focused on developing a deep learning model for sentiment analysis in Urdu and created an open-source corpus with 10,008 reviews. Using various models for binary and ternary classification studies, the RCNN model showed excellent performance with high accuracy rates in both classification tasks.
Review
Computer Science, Artificial Intelligence
Jing Zhang, Aijia Zhang, Dian Liu, Yiwen Bian
Summary: Consumers are increasingly concerned about air quality, leading to fierce competition in the air purifier market. By utilizing fine-grained sentiment analysis and the Kano model, consumer demands for product attributes can be extracted from online reviews, aiding in improving product design and enhancing competitiveness.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Zhenyu Zhang, Jian Guo, Huirong Zhang, Lixin Zhou, Mengjiao Wang
Summary: This article presents a product selection model based on sentiment analysis and intuitionistic fuzzy TODIM method, which helps consumers make more reasonable purchasing decisions by extracting product features and sentiment orientation from online reviews.
COMPLEX & INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zhaolong Ling, Bo Li, Yiwen Zhang, Ying Li, Haifeng Ling
Summary: This article proposes two new algorithms, O-ST and O-DC, to address the issues in online Markov blanket learning. Experimental results demonstrate that these algorithms outperform existing methods in terms of efficiency and accuracy.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Slavko Zitnik, Neli Blagus, Marko Bajec
Summary: The rapid growth of social media, news sites, and blogs has led to an increase in expressing and sharing opinions on the internet. Opinion mining or sentiment analysis has become an important research discipline in the past decade. This paper focuses on target-level sentiment analysis, where the task is to predict the sentiment towards specific entities mentioned throughout the document. The study presents a new annotated dataset of Slovene news articles and compares the task with traditional sentiment analysis using various machine learning and deep neural network approaches. The results demonstrate the effectiveness of a customized BERT adapter in achieving the best results.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Multidisciplinary Sciences
Yu Wen, Yezhang Liang, Xinhua Zhu
Summary: The emotion analysis of hotel online reviews is conducted using the BERT neural network model, which proves its effectiveness in understanding customer needs, helping customers find suitable hotels, and enhancing hotel recommendations. This research also explores the use of the ERNIE model as an enhancement to BERT, demonstrating its superior performance in classification and stability.
