Computational Collective Intelligence: 17th International Conference, ICCCI 2025, Ho Chi Minh City, Vietnam, November 12–15, 2025, Proceedings, Part I(16138 Lecture Notes in Computer Science)

This two-set volume LNAI 16138-16139 constitutes the refereed proceedings of the 17th International Conference on Computational Collective Intelligence, ICCCI 2025, held in Ho Chi Minh City, Vietnam, during November 12-15, 2025. The 67 revised full papers presented in these proceedings were carefully reviewed and selected from 290 submissions. The papers are organized in the following topical sections: Part I: Collective Intelligence and Collective Decision-Making; Co-operative Strategies for Decision-Making & Optimisation; Natural Language Processing; Knowledge Engineering & Industry 4.0 Applications; Data Mining & Machine Learning. Part II: Social Networks and Intelligent Systems; Cyber-Security, Blockchain & IoT; Computational Intelligence in Medical Applications; Computational Intelligence for Digital Content Understanding.

Table of Contents:
.-Collective Intelligence and Collective Decision-Making:Towards Trustworthy Legal AI: a Multi-Agent Approach to Integrating Legislative Knowledge.-Evaluating Theory of Mind and Internal Beliefs in LLM-Based Multi-Agent Systems.-A Multi-Agent System Based on Learning Automata for Solving the Coverage Problem in Self-Organizing Wireless Sensor Networks.-Automatic Assessment of Verbal Communication Components in Group Processes.-Hypersphere-Based Multimodal Knowledge Graph Completion with DURA Regularization.-On the Semantic Complexity of Association Relationships in Conceptual Modeling Languages.-Co-operative Strategies for Decision-Making & Optimisation:Minimax regret scheduling problem on unrelated machines with two uncertain parameters.-A Two-Step Approach to Modeling and Solving the University Course Timetabling Problem.-A Lightweight Drift Aware Aggregation Method for Time Series Forecasting.-Secure Cooperative Semantic Communication with Swin Transformer and Jamming.-A Causal Inference Approach to Assess the Effects of Atomic Concentration Changes on the Hardness of High-Entropy Alloys.-Privacy-Aware Knowledge Transfer for Cross-domain Recommender System.-Natural Language Processing:DESS: DeBERTa Enhanced Syntactic-Semantic Aspect Sentiment Triplet Extraction.-Text-JEPA: A Joint Embedding Predictive Architecture for the Conversion of Natural Language into First-Order Logic.-RAG-ViVerse: Enhancing Poetry Generation With Retrieval Augmented Generation and Large Language Models.-ViPhoVQA: Toward a Phonemic-Based Method for Mitigating Rare and Out-of-Vocab Words in Vietnamese Text-based Visual Question Answering.-Evaluating the Strategy to Deploy Large Language Models to Label Training Data in the Process of Fake News Detection.-Towards Complex Question Answering in Polish Language.-Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining.-A Hybrid Ensemble Framework for Topic Extraction in Vietnamese Legal Documents.-Knowledge Engineering & Industry 4.0 Applications:Code Similarity Detection Using Complexity-Based Birthmarks.-Balanced Assessment of Programmers’ Contribution in IT Projects.-A Systematic Approach to Measuring Developer Productivity: The Prismetrix Method.-LLMs as Code Review Agents: A Rapid Review and Experimental Evaluation with Human Expert Judges.-Enhancing Hotspot Detection with Behavioral Analysis and AI-Assisted Code Review.-Data Mining & Machine Learning:Efficient Algorithms for Mining Top-rank-k Frequent Closed Inter-transaction Patterns.-Mining Top-rank-k frequent inter-transaction patterns.-Predicting Students Academic Performance by Processing the Imbalanced Education Dataset.-Leveraging a Machine Learning Method for Continuous Segmentation of Airways in Videobronchoscopy.-Application of Whitebox Machine Learning Models for Optimizing Electrochemical Assays of Drug Permeability.-Enhancing Bagging Ensemble Regression with Data Integration for Time Series-Based Diabetes Prediction.-A Light and Efficient Framework for e-Commerce Fraud Detection.-Convenient time series features extraction package FExtract.