Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Application of Artificial Intelligence Methods in Processing of Emotions, Decisions...
share announcement

Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (31 March 2024) | Viewed by 14463

Special Issue Editors

Dr. Pawel Dybala

E-Mail Website
Guest Editor
Institute of the Middle and Far East, Faculty of International and Political Studies, Jagiellonian University, 30-063 Krakow, Poland
Interests: natural language processing; dialogue processing; humor processing; HCI; information retrieval
Special Issues, Collections and Topics in MDPI journals
Dr. Rafal Rzepka

E-Mail Website
Guest Editor
School of Information Science and Technology, Hokkaido University, Hokkaido 060-0808, Japan
Interests: natural language processing; common sense knowledge retrieval; dialogue processing; artificial general intelligence; affect and sentiment analysis; machine ethics
Special Issues, Collections and Topics in MDPI journals
Dr. Michal Ptaszynski

E-Mail Website
Guest Editor
Text Information Processing Laboratory, Kitami Institute of Technology, 165 Koen-cho, Kitami 090-8507, Japan
Interests: natural language processing; artificial intelligence
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

During recent years, social infrastructure has become irreversibly linked to the Internet through its everyday manifestations, such as social networking services (Twitter, Facebook, etc.). Every second this new tangible information-based reality provides large amounts of data filled with 1) emotional expressions; 2) people's opinions on various topics; and 3) their reasoning, revealing their decision-making processes. As these three categories are also closely interrelated with each other, they should be studied together to obtain a more robust view on all of the topics involved. This, as never before, provides an opportunity for the development and application of natural language processing methods, in particular those regarding such topics as emotion processing, decision making, and opinion mining.

For this issue, we invite high-quality papers from researchers with interest in knowing more about those topics and their connection to the world we live in by the means of opinion and sentiment analysis, recommendation systems, web mining, automated decision making, etc. We also invite papers on the topic of using Natural Language Processing tools and methods to process emotions, metaphors, ethics, or other phenomena related to human activities.

Dr. Pawel Dybala
Dr. Rafal Rzepka
Dr. Michal Ptaszynski
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • emotions
  • decisions
  • opinions
  • NLP
  • AI
  • linguistics
  • cognitive science

Published Papers (7 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

32 pages, 1277 KiB  
Article
Automatic Vulgar Word Extraction Method with Application to Vulgar Remark Detection in Chittagonian Dialect of Bangla
by Tanjim Mahmud, Michal Ptaszynski and Fumito Masui
Appl. Sci. 2023, 13(21), 11875; https://doi.org/10.3390/app132111875 - 30 Oct 2023
Cited by 7 | Viewed by 983
Abstract
The proliferation of the internet, especially on social media platforms, has amplified the prevalence of cyberbullying and harassment. Addressing this issue involves harnessing natural language processing (NLP) and machine learning (ML) techniques for the automatic detection of harmful content. However, these methods encounter [...] Read more.
The proliferation of the internet, especially on social media platforms, has amplified the prevalence of cyberbullying and harassment. Addressing this issue involves harnessing natural language processing (NLP) and machine learning (ML) techniques for the automatic detection of harmful content. However, these methods encounter challenges when applied to low-resource languages like the Chittagonian dialect of Bangla. This study compares two approaches for identifying offensive language containing vulgar remarks in Chittagonian. The first relies on basic keyword matching, while the second employs machine learning and deep learning techniques. The keyword-matching approach involves scanning the text for vulgar words using a predefined lexicon. Despite its simplicity, this method establishes a strong foundation for more sophisticated ML and deep learning approaches. An issue with this approach is the need for constant updates to the lexicon. To address this, we propose an automatic method for extracting vulgar words from linguistic data, achieving near-human performance and ensuring adaptability to evolving vulgar language. Insights from the keyword-matching method inform the optimization of machine learning and deep learning-based techniques. These methods initially train models to identify vulgar context using patterns and linguistic features from labeled datasets. Our dataset, comprising social media posts, comments, and forum discussions from Facebook, is thoroughly detailed for future reference in similar studies. The results indicate that while keyword matching provides reasonable results, it struggles to capture nuanced variations and phrases in specific vulgar contexts, rendering it less robust for practical use. This contradicts the assumption that vulgarity solely relies on specific vulgar words. In contrast, methods based on deep learning and machine learning excel in identifying deeper linguistic patterns. Comparing SimpleRNN models using Word2Vec and fastText embeddings, which achieved accuracies ranging from 0.84 to 0.90, logistic regression (LR) demonstrated remarkable accuracy at 0.91. This highlights a common issue with neural network-based algorithms, namely, that they typically require larger datasets for adequate generalization and competitive performance compared to conventional approaches like LR. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions)
►▼ Show Figures

Figure 1

18 pages, 3359 KiB  
Article
Social Media Opinion Analysis Model Based on Fusion of Text and Structural Features
by Jie Long, Zihan Li, Qi Xuan, Chenbo Fu, Songtao Peng and Yong Min
Appl. Sci. 2023, 13(12), 7221; https://doi.org/10.3390/app13127221 - 16 Jun 2023
Viewed by 1152
Abstract
The opinion recognition for comments in Internet media is a new task in text analysis. It takes comment statements as the research object, by learning the opinion tendency in the original text with annotation, and then performing opinion tendency recognition on the unannotated [...] Read more.
The opinion recognition for comments in Internet media is a new task in text analysis. It takes comment statements as the research object, by learning the opinion tendency in the original text with annotation, and then performing opinion tendency recognition on the unannotated statements. However, due to the uncertainty of NLP (natural language processing) in short scenes and the complexity of Chinese text, existing methods have some limitations in accuracy and application scenarios. In this paper, we propose an opinion tendency recognition model HGAT (heterogeneous graph attention network) that integrates text vector and context structure methods to address the above problems. This method first trains a text vectorization model based on annotation text content, then constructs an isomorphic graph with annotation, news, and theme as its apex, and then optimizes the feature vectors of all nodes using an isomorphic graph neural network model with attention mechanism. In addition, this article collected 1,684,318 news items and 57,845,091 comments based on Toutiao, sifted through 511 of those stories and their corresponding 103,787 comments, and tested the impact of HGAT on this dataset. Experiments show that this method has stable improvement effect on different NLP methods, increasing accuracy by 2–10%, and provides a new perspective for opinion tendency recognition. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions)
►▼ Show Figures

Figure 1

15 pages, 8580 KiB  
Article
Emotional State Detection Using Electroencephalogram Signals: A Genetic Algorithm Approach
by Rosa A. García-Hernández, José M. Celaya-Padilla, Huizilopoztli Luna-García, Alejandra García-Hernández, Carlos E. Galván-Tejada, Jorge I. Galván-Tejada, Hamurabi Gamboa-Rosales, David Rondon and Klinge O. Villalba-Condori
Appl. Sci. 2023, 13(11), 6394; https://doi.org/10.3390/app13116394 - 23 May 2023
Cited by 3 | Viewed by 1570
Abstract
Emotion recognition based on electroencephalogram signals (EEG) has been analyzed extensively in different applications, most of them using medical-grade equipment in laboratories. The trend in human-centered artificial intelligence applications is toward using portable sensors with reduced size and improved portability that can be [...] Read more.
Emotion recognition based on electroencephalogram signals (EEG) has been analyzed extensively in different applications, most of them using medical-grade equipment in laboratories. The trend in human-centered artificial intelligence applications is toward using portable sensors with reduced size and improved portability that can be taken to real life scenarios, which requires systems that efficiently analyze information in real time. Currently, there is no specific set of features or specific number of electrodes defined to classify specific emotions using EEG signals, and performance may be improved with the combination of all available features but could result in high dimensionality and even worse performance; to solve the problem of high dimensionality, this paper proposes the use of genetic algorithms (GA) to automatically search the optimal subset of EEG data for emotion classification. Publicly available EEG data with 2548 features describing the waves related to different emotional states are analyzed, and then reduced to 49 features with genetic algorithms. The results show that only 49 features out of the 2548 can be sufficient to create machine learning (ML) classification models with, using algorithms such as k-nearest neighbor (KNN), random forests (RF) and artificial neural networks (ANN), obtaining results with 90.06%, 93.62% and 95.87% accuracy, respectively, which are higher than the 87.16% and 89.38% accuracy of previous works. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions)
►▼ Show Figures

Figure 1

26 pages, 1394 KiB  
Article
Affect Analysis in Arabic Text: Further Pre-Training Language Models for Sentiment and Emotion
by Wafa Alshehri, Nora Al-Twairesh and Abdulrahman Alothaim
Appl. Sci. 2023, 13(9), 5609; https://doi.org/10.3390/app13095609 - 01 May 2023
Cited by 1 | Viewed by 2136
Abstract
One of the main tasks in the field of natural language processing (NLP) is the analysis of affective states (sentiment and emotional) based on written text, and attempts have improved dramatically in recent years. However, in studies on the Arabic language, machine learning [...] Read more.
One of the main tasks in the field of natural language processing (NLP) is the analysis of affective states (sentiment and emotional) based on written text, and attempts have improved dramatically in recent years. However, in studies on the Arabic language, machine learning or deep learning algorithms were utilised to analyse sentiment and emotion more often than current pre-trained language models. Additionally, further pre-training the language model on specific tasks (i.e., within-task and cross-task adaptation) has not yet been investigated for Arabic in general, and for the sentiment and emotion task in particular. In this paper, we adapt a BERT-based Arabic pretrained language model for the sentiment and emotion tasks by further pre-training it on a sentiment and emotion corpus. Hence, we developed five new Arabic models: QST, QSR, QSRT, QE3, and QE6. Five sentiment and two emotion datasets spanning both small- and large-resource settings were used to evaluate the developed models. The adaptation approaches significantly enhanced the performance of seven Arabic sentiment and emotion datasets. The developed models showed excellent improvements over the sentiment and emotion datasets, which ranged from 0.15–4.71%. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions)
►▼ Show Figures

Figure 1

35 pages, 1205 KiB  
Article
Personality Types and Traits—Examining and Leveraging the Relationship between Different Personality Models for Mutual Prediction
by Dušan Radisavljević, Rafal Rzepka and Kenji Araki
Appl. Sci. 2023, 13(7), 4506; https://doi.org/10.3390/app13074506 - 02 Apr 2023
Cited by 2 | Viewed by 3402
Abstract
The popularity of social media services has led to an increase of personality-relevant data in online spaces. While the majority of people who use these services tend to express their personality through measures offered by the Myers–Briggs Type Indicator (MBTI), another personality model [...] Read more.
The popularity of social media services has led to an increase of personality-relevant data in online spaces. While the majority of people who use these services tend to express their personality through measures offered by the Myers–Briggs Type Indicator (MBTI), another personality model known as the Big Five has been a dominant paradigm in academic works that deal with personality research. In this paper, we seek to bridge the gap between the MBTI, Big Five and another personality model known as the Enneagram of Personality, with the goal of increasing the amount of resources for the Big Five model. We further explore the relationship that was previously reported between the MBTI types and certain Big Five traits as well as test for the presence of a similar relationship between Enneagram and Big Five measures. We propose a new method relying on psycholingusitc features selected based on their relationship with the MBTI model. This approach showed the best performance through our experiments and led to an increase of up to 3% in automatic personality recognition for Big Five traits on the per-trait level. Our detailed experimentation offers further insight into the nature of personality and into how well it translates between different personality models. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions)
►▼ Show Figures

Figure 1

16 pages, 2325 KiB  
Article
Understanding of Customer Decision-Making Behaviors Depending on Online Reviews
by Yeo-Gyeong Noh, Junryeol Jeon and Jin-Hyuk Hong
Appl. Sci. 2023, 13(6), 3949; https://doi.org/10.3390/app13063949 - 20 Mar 2023
Cited by 1 | Viewed by 2165
Abstract
With a never-ending stream of reviews propagating online, consumers encounter countless good and bad reviews. Depending on which reviews consumers read, they get a different impression of the product. In this paper, we focused on the relationship between the text and numerical information [...] Read more.
With a never-ending stream of reviews propagating online, consumers encounter countless good and bad reviews. Depending on which reviews consumers read, they get a different impression of the product. In this paper, we focused on the relationship between the text and numerical information of reviews to gain a better understanding of the decision-making process of consumers affected by the reviews. We evaluated the decisions that consumers made when encountering the review structure of star ratings paired with comments, with respect to three research questions: (1) how consumers compare two products with reviews, (2) how they individually perceive a product based on the corresponding reviews, and (3) how they interpret star ratings and comments. Through the user study, we confirmed that consumers consider reviews differently according to product presentation conditions. When consumers were comparing products, they were more influenced by star ratings, whereas when they were evaluating individual products, they were more influenced by comments. Additionally, consumers planning to buy a product examined star ratings by more stringent criteria than those who had already purchased the product. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions)
►▼ Show Figures

Figure 1

Review

Jump to: Research

19 pages, 2231 KiB  
Review
Fake News Detection on Social Networks: A Survey
by Yanping Shen, Qingjie Liu, Na Guo, Jing Yuan and Yanqing Yang
Appl. Sci. 2023, 13(21), 11877; https://doi.org/10.3390/app132111877 - 30 Oct 2023
Viewed by 1665
Abstract
In recent years, social networks have developed rapidly and have become the main platform for the release and dissemination of fake news. The research on fake news detection has attracted extensive attention in the field of computer science. Fake news detection technology has [...] Read more.
In recent years, social networks have developed rapidly and have become the main platform for the release and dissemination of fake news. The research on fake news detection has attracted extensive attention in the field of computer science. Fake news detection technology has made many breakthroughs recently, but many challenges remain. Although there are some review papers on fake news detection, a more detailed picture for carrying out a comprehensive review is presented in this paper. The concepts related to fake news detection, including fundamental theory, feature type, detection technique and detection approach, are introduced. Specifically, through extensive investigation and complex organization, a classification method for fake news detection is proposed. The datasets of fake news detection in different fields are also compared and analyzed. In addition, the tables and pictures summarized here help researchers easily grasp the full picture of fake news detection. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence Methods in Processing of Emotions, Decisions and Opinions)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-7
Back to TopTop