Multi-agent debate (MAD) frameworks have emerged as promising approaches for misinformation detection by simulating adversarial reasoning. While prior work has focused on detection accuracy, the importance of helping users understand the reasoning behind factual judgments has been overlooked. The debate transcripts generated during MAD offer a rich but underutilized resource for transparent reasoning. In this study, we introduce ED2D, an evidence-based MAD framework that extends previous approach by incorporating factual evidence retrieval. More importantly, ED2D is designed not only as a detection framework but also as a persuasive multi-agent system aimed at correcting user beliefs and discouraging misinformation sharing. We compare the persuasive effects of ED2D-generated debunking transcripts with those authored by human experts. Results demonstrate that ED2D outperforms existing baselines across three misinformation detection benchmarks. When ED2D generates correct predictions, its debunking transcripts exhibit persuasive effects comparable to those of human experts; However, when ED2D misclassifies, its accompanying explanations may inadvertently reinforce users’ misconceptions, even when presented alongside accurate human explanations. Our findings highlight both the promise and the potential risks of deploying MAD systems for misinformation intervention. We further develop a public community website to help users explore ED2D, fostering transparency, critical thinking, and collaborative fact-checking.

Chinese policy documents are typically written in a concise yet contextually rich style, containing implicit hierarchical logic and strategic intent. These linguistic and structural features present challenges for traditional information extraction methods, which often struggle with cross-sentence dependencies and semantic complexity. To address these, we propose DocPolicyKG, a novel framework for constructing knowledge graphs from Chinese policy documents using lightweight large language models (LLMs), integrating domain ontology, fine-tuning, and prompt engineering. Focusing on the investment promotion policies in China, experimental results demonstrate that DocPolicyKG significantly outperforms the base model Deepseek-R1-7B and achieves performance competitive with GPT-4o on both named entity recognition (NER) and relation triplet extraction (RTE) tasks. Building on DocPolicyKG, we construct the first large-scale knowledge graph of Chinese investment promotion policies, and further integrate Graph Retrieval-Augmented Generation (Graph RAG) to support policy question answering through entity-relation reasoning and semantic retrieval. The graph data is publicly available at: github.com/hanshenmesen/DocPolicyKG.

The proliferation of misinformation in digital platforms reveals the limitations of traditional detection methods, which mostly rely on static classification and fail to capture the intricate process of real-world fact-checking.Despite advancements in Large Language Models (LLMs) that enhance automated reasoning, their application to misinformation detection remains hindered by issues of logical inconsistency and superficial verification.Inspired by the idea that "Truth Becomes Clearer Through Debate", we introduce Debate-to-Detect (D2D), a novel Multi-Agent Debate (MAD) framework that reformulates misinformation detection as a structured adversarial debate.Based on fact-checking workflows, D2D assigns domain-specific profiles to each agent and orchestrates a five-stage debate process, including Opening Statement, Rebuttal, Free Debate, Closing Statement, and Judgment.To transcend traditional binary classification, D2D introduces a multi-dimensional evaluation mechanism that assesses each claim across five distinct dimensions: Factuality, Source Reliability, Reasoning Quality, Clarity, and Ethics.Experiments with GPT-4o on two fakenews datasets demonstrate significant improvements over baseline methods, and the case study highlight D2D's capability to iteratively refine evidence while improving decision transparency, representing a substantial advancement towards robust and interpretable misinformation detection.Our code is available at Debate-to-Detect.

Using the posts of Tianya Forum as the data source and adopting the societal risk indicators from socio psychology, we conduct document-level multiple societal risk classification of BBS posts. Two kinds of models are applied to generate the representations of posts respectively: Bag-of-Words focuses on extracting the occurrence information of words in posts, and a deep learning model as Post Vector is designed to capture the semantics and word order of posts. Based on the different post representations, two types of support vector machine (SVM) classifiers are developed and compared in the societal risk classification of the posts. Furthermore, as the complementary information contained in the two different post representations, several SVM ensemble methods at the decision score level of the two SVM classifiers are proposed to improve the performance of societal risk classification. The experimental results reveal that the SVM ensemble method achieves better results in document-level societal risk classification than SVM based on single representation.

Using the posts of Tianya Forum as the data source and adopting the socio psychology study results on societal risks perception, we analyze the challenges and feasibility of the document-level multiple societal risk classification of BBS posts. To effectively capture the semantics and word order of documents, a deep learning model as Post Vector is applied to realize the distributed vector representations of the posts in the vector space. Based on the distributed vector representations, cross-validated classification of the posts labeled by different annotators with KNN method and pair wise similarities comparisons of the posts between risk categories are implemented. The big variance of the results of cross validation shows the differences of individual risk perceptions, which reflects the challenges of societal risk classification. Furthermore, the higher similarities of posts in same societal risk category manifest the feasibility of the classification of societal risks, and indicate the possibility to improve the performance of the societal risk classification of BBS posts.

Modern China is exposed to many societal risks. The risk perception induced emotion at the individual level but their relationship on a large scale is costly to assess, while some social emotional reactions such as anger may evoke collective actions. The seven societal risk perceptions including social stability, daily life, resource & environment, public moral, government management, national security and economic & finance were gotten on the basis of the public searching behavior on Baidu search engine. The five public moods including Happiness, Sadness, Fear, Anger and Disgust were obtained by analyzing the text content of daily Sina Weibo. The relationship between the societal risk perceptions and public moods using Granger causality analysis was that the societal risk perceptions are predictive of public moods but the effect of different kinds of societal risk perception is distinguishing. This research manifested that capturing public psychological characteristics on social media was feasible.

Hesitant fuzzy linguistic term set (HFLTS) is a set with ordered consecutive linguistic terms, and is very useful in addressing the situations where people are hesitant in providing their linguistic assessments. Wang [H. Wang, Extended hesitant fuzzy linguistic term sets and their aggregation in group decision making, International Journal of Computational Intelligence Systems 8(1) (2015) 14–33.] removed the consecutive condition to introduce the notion of extended HFLTS (EHFLTS). The generalized form has wider applications in linguistic group decision-making. By introducing distance measures for EHFLTSs, in this paper we develop a novel multi-criteria group decision making model to deal with hesitant fuzzy linguistic information. The model collects group linguistic information by using EHFLTSs and avoids the possible loss of information. Moreover, it can assess the importance weights of criteria according to their subjective and objective information and rank alternatives based on the rationale of TOPSIS. In order to illustrate the applicability of the proposed algorithm, two examples are given and comparisons are made with the other existing methods.

The theory of hesitant fuzzy linguistic term sets (HFLTSs) is very useful in objectively dealing with situations in which people are hesitant in providing linguistic assessments. The purpose of this paper is to develop comparison methods and study the aggregation theory for HFLTSs. We first define operations on HFLTSs and give possibility degree formulas for comparing HFLTSs. We then define two aggregation operators for HFLTSs: a hesitant fuzzy LWA operator and a hesitant fuzzy LOWA operator. In actual application, we use these operators and the comparison methods to deal with multicriteria decision-making problems with different situations in which importance weights of criteria or experts are known or unknown.

Current China is undergoing social transformation with economic miracle and emerging big poor-rich gap. Mission to a Harmonious Society has been promoted by Chinese top leaders. This paper briefly outlines several indicators to evaluate the harmony society. As a variety of Internet tools provides ways to record and disseminate fresh community opinions conveniently, mining of those kinds of public opinions is expected. This paper discusses one approach to societal risk perception using hot search words and BBS posts, which aims to provide another access to societal risk perception different from those in traditional socio psychology studies. Problems are also indicated.

This paper deals with multicriteria decision-making problems in which the criteria are partitioned into q categories, and a prioritization relationship exists over categories. We aggregate the criteria in the same priority category by a weighted OWA (ordered weighted averaging) operator and introduce two averaging operators, a generalized prioritized averaging operator and a generalized prioritized OWA operator. In the case with one criterion in each priority category, the two operators reduce to the prioritized averaging operator and the prioritized OWA operator as proposed by Yager. © 2012 Wiley Periodicals, Inc.

Proposed by Chinese system scientists in 1990, meta-synthesis approach is a system methodology to tackle complex system problems. Till today, this approach still lacks well understanding at home and abroad which then blocks its development. This paper addresses MSA by DSS, soft OR methods or the relevant computerized support so as to explain the working philosophy of the approach and provide help to apply the approach to practical problem solving or the construction of its practicing platform, i.e. Hall for Workshop of Meta-synthetic Engineering (HWMSE) by adopting available methods or developing new technologies. The latter part briefly addresses two technologies, CorMap and iView, which conduct a computing way to support qualitative meta-synthesis for hypothesis generation for further verification and validation. Four typical applications are given.

Systems methodologies toward wicked problems or societal complex systems usually call for a collaborative problem solving process. The products (solutions) of that process refer to somewhat collective intelligence. In this paper, some technologies for collective intelligence, or so-called qualitative meta-synthesis of community consensus, are addressed. Two technologies, CorMap and iView, conduct exploratory analysis toward those topics or ideas created bottom-up and facilitate human-machine interaction by visualization of the analytical process based on different algorithms. Those technologies are oriented to support collaborative deliberation undertaken by Web 2.0 tools.

Along with the fast-growth in both scale and frequency of academic conferences and advances in communication and information technologies, digital revolutions are happening to conferencing affairs. Paper review assignment is a hard and time-consuming job due to many constraints, even emotional factors affect the review assignment. In this paper, the human-knowledge network, aggregated based on the past conference publications, social networks of PC members' or practical reviewers' and their expertise, is adopted into paper review assignment to tackle those constraints so as to generate an integer programming model to produce optimal alternatives for practical assignment..

Text representation, which is a fundamental and necessary process for text-based intelligent information processing, includes the tasks of determining the index terms for documents and producing the numeric vectors corresponding to the documents. In this paper, multi-word, which is regarded as containing more contextual semantics than individual word and possessing the favorable statistical characteristics, is proposed as an alternative index terms in vector space model for text representation with theoretical support. We investigate the traditional indexing methods as TF*IDF (term frequency inverse document frequency) and LSI (latent semantic indexing) for comparative study. The performances of TF*IDF, LSI and multi-word are examined on the tasks of text classification, which includes information retrieval (IR) and text categorization (TC), in Chinese and English document collection respectively. We also attempt to tune the rescaling factor of LSI and observe its effectiveness in text classification. The experimental results demonstrate that TF*IDF and multi-word are comparable when they are used for IR and TC and LSI is the poorest one of them. Moreover, the rescaling factor of LSI has an insignificant influence on its effectiveness on text classification for both Chinese and English text classification.

Traditional Chinese medicine (TCM) has a rich knowledge about human health and disease by its special way evolved along a very long history. As modern medicine is achieving much progress, arguments and disputes toward TCM never ends. To avoid losing lots of precious knowledge of TCM masters, endeavors have been engaged to systematic collection of those knowledge of TCM masters, such as their growth experiences, effective practical cases toward sickness and typical therapeutic principles and methods. Various knowledge mining has been expected to explore some useful or hidden patterns to unveil some mysteries of TCM system. This paper describes a computerized tool, TCM Master Miner, which applies different analytical methods to those collected materials about some living TCM masters in China mainland to show a different way of exposing essential ideas of those TCM masters by correspondence visualization which aims to help people understand TCM holistic views toward disease and body, and facilitate tacit knowledge transfer and sense-making of the TCM essence. This work is one kind of qualitative meta-synthesis of TCM masters' knowledge.

We carried out a series of experiments on text classification using multi-word features. An automated method was proposed to extract the multi-words from text data set and two different strategies were developed to normalize the multi-words into two different versions of multi-word features. After the texts were represented respectively using these two different multi-word features, text classification was conducted in contrast to examine the effectiveness of these two strategies. Also the linear and nonlinear polynomial kernel of support vector machine (SVM) was compared on the performance of text classification task.