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

1. Introduction

The rapid advancement of artificial intelligence (AI) and natural language processing (NLP) has profoundly impacted our understanding of emotions, decision-making, and opinions, particularly within the context of the Internet and social media. This special issue of Applied Sciences, titled “Application of Artificial Intelligence Methods in Processing of Emotions, Decisions, and Opinions”, brings together a collection of pioneering research articles that study these intertwined domains. This issue aims to highlight innovative AI methodologies and their application in analyzing and understanding the intricate human experiences reflected in online data. We discuss the accepted papers in their respective thematic groups.

2. Understanding Human Decision-Making through AI

Yuan Zhou and Siamak Khatibi [1], in their paper A New AI Approach by Acquisition of Characteristics in Human Decision-Making Process, challenge the conventional Markovian decision-making models by proposing an ambiguity probability model that captures the dynamic nature of human decision strategies. Their innovative decision map approach offers a nuanced understanding of human decision dependencies, presenting a significant advancement in modeling complex decision-making processes.

3. Enhancing Educational Assessments and Course Improvement

Maresha Caroline Wijanto and Hwan-Seung Yong [2] address the challenges of automatic short-answer grading in their paper Combining Balancing Dataset and SentenceTransformers to Improve Short Answer Grading Performance. By integrating a balanced dataset with a simplified SentenceTransformers model, they achieve high grading accuracy, demonstrating that efficient and cost-effective AI models can rival more resource-intensive techniques.

In the realm of online education, Pei Yang Ying Liu, Yuyan Luo, Zhong Wang and Xiaoli Cai [3] present Text Mining and Multi-Attribute Decision-Making-Based Course Improvement in Massive Open Online Courses. Their method combines text mining and decision-making techniques to extract and analyze learner feedback, providing actionable insights for enhancing course quality and learner satisfaction.

4. Detecting and Analyzing Offensive Language

The proliferation of social media has necessitated robust methods for detecting harmful content. Tanjim Mahmud, Michal Ptaszynski and Fumito Masui [4] tackle this issue in Automatic Vulgar Word Extraction Method with Application to Vulgar Remark Detection in Chittagonian Dialect of Bangla. By comparing keyword matching with advanced machine learning techniques, they highlight the efficacy of deep learning in capturing nuanced vulgar language, particularly in low-resource languages and dialects.

5. Opinion and Emotion Analysis in Social Media

Jie Long, Zihan Li, Qi Xuan, Chenbo Fu, Songtao Peng and Yong Min [5] introduce an innovative model in their paper Social Media Opinion Analysis Model Based on Fusion of Text and Structural Features. Their heterogeneous graph attention network (HGAT) effectively integrates text and contextual data, enhancing the accuracy of opinion recognition in complex Chinese texts, thereby contributing significantly to the field of sentiment analysis.

Wafa Alshehri, Nora Al-Twairesh and Abdulrahman Alothaim [6] study emotion detection in Arabic texts with their work Affect Analysis in Arabic Text: Further Pre-Training Language Models for Sentiment and Emotion. By adapting BERT-based models for Arabic sentiment and emotion tasks, they achieve notable improvements, showcasing the potential of pre-trained language models in underrepresented languages.

6. Integrating Cognitive Science and AI

Rosa A. García-Hernández and her research team [7] explore the intersection of cognitive science and AI in their paper Emotional State Detection Using Electroencephalogram Signals: A Genetic Algorithm Approach. Utilizing genetic algorithms to optimize EEG data features, they achieve impressive accuracy in emotion classification, paving the way for real-time emotion detection using portable sensors.

7. Understanding Consumer Behavior

In Understanding of Customer Decision-Making Behaviors Depending on Online Reviews, Yeo-Gyeong Noh, Junryeol Jeon and Jin-Hyuk Hong [8] study how consumers process online reviews. Their findings reveal the differential impact of star ratings and comments on consumer decisions, providing valuable insights for businesses aiming to leverage online reviews to influence purchasing behavior.

8. Personality Analysis in Social Media

Dušan Radisavljević, Rafal Rzepka, and Kenji Araki [9] investigate the relationship between various personality models in their paper Personality Types and Traits—Examining and Leveraging the Relationship between Different Personality Models for Mutual Prediction. By bridging the gap between MBTI, Big Five, and Enneagram models, they enhance the resources available for personality research, offering new methods for personality recognition.

9. Comprehensive Review on Fake News Detection

Finally, the review article Fake News Detection on Social Networks: A Survey by Yanping Shen, Qingjie Liu, Na Guo, Jing Yuan and Yanqing Yang [10] provides a comprehensive overview of the current state of fake news detection. Their detailed classification of detection techniques and analysis of datasets serves as a valuable resource for researchers dedicated to combating the spread of misinformation.

10. Conclusions

This special issue of Applied Sciences showcases the cutting-edge advancements in AI methods for processing emotions, decisions, and opinions. The diverse range of studies presented here not only underscores the interdisciplinary nature of this field but also highlights the transformative potential of AI in understanding and addressing complex human behaviors in the digital age. We hope these contributions will inspire further research and innovation, driving the continued evolution of AI and its applications in society.