Information Processing & Management最新文献

{"title":"A three-way efficacy prediction method fusing temporal composite rough set and hybrid machine learning models on multigranulation temporal hybrid attribute information system","authors":"Xixuan Zhao ,&nbsp;Bingzhen Sun ,&nbsp;Jin Ye ,&nbsp;Jiqian Liu ,&nbsp;Xinfang Zhang ,&nbsp;Haoran Sun ,&nbsp;Xiaoli Chu","doi":"10.1016/j.ipm.2025.104300","DOIUrl":"10.1016/j.ipm.2025.104300","url":null,"abstract":"<div><div>Efficacy prediction is a key research topic in clinical management practice. To address the general efficacy prediction problem characterized by multigranularity, temporality, and incompleteness, this study proposes a three-way efficacy prediction method that integrates a temporal composite rough set and a hybrid machine learning model (TCRS-HML). First, a multigranulation temporal hybrid attribute information system (MTHAIS) is constructed to handle hybrid attributes exhibiting these characteristics, and the data in MTHAIS is preprocessed using random forest and bag-of-words models. Next, the concept of temporal order is introduced into classical composite rough sets, and temporal equivalence, temporal neighborhood, and temporal similarity relationships are established based on the temporal hybrid attribute matrices of the objects. Subsequently, the definitions of a temporal composite rough set and its attribute reduction method are presented, along with a discussion of their mathematical properties. Finally, efficacy prediction results are obtained by building a hybrid machine learning model pool and selecting the optimal model. Experimental results, based on 493 real temporal medical records from 120 rheumatoid arthritis (RA) patients at the Guangdong Hospital of Traditional Chinese Medicine (2018–2023), show that the accuracy, precision, recall, and F<span><math><msub><mrow></mrow><mrow><mn>1</mn></mrow></msub></math></span> score of the proposed method are 0.8012, 0.8241, 0.8012, and 0.7885, respectively. These results outperform those of 17 comparative methods, demonstrating the scientific validity and feasibility of proposed approach. Furthermore, sensitivity analyses and statistical tests confirm the robustness and generalizability of the method. This study provides a new methodological reference for management science problems such as clinical efficacy prediction and contributes to the integration of rough set theory and machine learning in management and decision sciences.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104300"},"PeriodicalIF":7.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144679303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large language models for scholarly ontology generation: An extensive analysis in the engineering field","authors":"Tanay Aggarwal ,&nbsp;Angelo Salatino ,&nbsp;Francesco Osborne ,&nbsp;Enrico Motta","doi":"10.1016/j.ipm.2025.104262","DOIUrl":"10.1016/j.ipm.2025.104262","url":null,"abstract":"<div><div>Ontologies of research topics are crucial for structuring scientific knowledge, enabling scientists to navigate vast amounts of research, and forming the backbone of intelligent systems such as search engines and recommendation systems. However, manual creation of these ontologies is expensive, slow, and often results in outdated and overly general representations. As a solution, researchers have been investigating ways to automate or semi-automate the process of generating these ontologies. One of the key challenges in this domain is accurately assessing the semantic relationships between pairs of research topics. This paper presents an analysis of the capabilities of large language models (LLMs) in identifying such relationships, with a specific focus on the field of engineering. To this end, we introduce a novel benchmark based on the IEEE Thesaurus for evaluating the task of identifying three types of semantic relations between pairs of topics: <em>broader</em>, <em>narrower</em>, and <em>same-as</em>. Our study evaluates the performance of seventeen LLMs, which differ in scale, accessibility (open vs. proprietary), and model type (full vs. quantised), while also assessing four zero-shot reasoning strategies. Several models with varying architectures and sizes have achieved excellent results on this task, including Mixtral-8<span><math><mo>×</mo></math></span> 7B, Dolphin-Mistral-7B, and Claude 3 Sonnet, with F1-scores of 0.847, 0.920, and 0.967, respectively. Furthermore, our findings demonstrate that smaller, quantised models, when optimised through prompt engineering, can achieve strong performance while requiring very limited computational resources.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104262"},"PeriodicalIF":7.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing knowledge graph interactions: A comprehensive Text-to-Cypher pipeline with large language models","authors":"Chao Yang ,&nbsp;Changyi Li ,&nbsp;Xiaodu Hu ,&nbsp;Hao Yu ,&nbsp;Jinzhi Lu","doi":"10.1016/j.ipm.2025.104280","DOIUrl":"10.1016/j.ipm.2025.104280","url":null,"abstract":"<div><div>Knowledge Graphs (KGs) store structured information but typically require specialized query languages, such as Cypher for Neo4j, creating accessibility challenges for users unfamiliar with graph syntax. Large Language Models (LLMs) offer a solution by translating natural language into Cypher queries. However, existing models—including large-scale LLMs (e.g., ChatGPT) and smaller open-source models (e.g., Llama-7B, 8B) often struggle with accurately generating domain-specific queries due to inadequate alignment with KG schemas and limited domain-specific training data. To address these limitations, we propose a training pipeline tailored specifically for domain-aligned Cypher query generation, emphasizing usability for smaller-scale models. Our method integrates template-based synthetic data generation for diverse, high-quality training samples. We combine supervised fine-tuning with preference learning to enhance domain knowledge and Cypher syntax understanding. Additionally, our approach includes a context-aware retrieval mechanism that dynamically incorporates relevant schema elements at inference, improving alignment with domain-specific knowledge. We evaluated our method on the Hetionet biomedical KG using a benchmark dataset of 240 queries across three complexity levels. Our results show that our context-aware prompting achieves a substantial improvement, increasing component matching accuracy by 23.6% for ChatGPT-4o over the vanilla prompt baseline. When applying our full training pipeline to smaller-scale models, CodeLlama-13B* achieves an execution accuracy of 69.2%, nearly matching ChatGPT-4o’s 72.1%. Importantly, our approach significantly narrows the performance gap, enabling smaller models to effectively manage complex, domain-specific tasks previously dominated by larger models. These findings demonstrate that our method is scalable, computationally efficient, and robust for practical Cypher query generation applications.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104280"},"PeriodicalIF":7.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Restaurant recommendations under multimodal online reviews: A novel method based on image captioning and text analysis with multi-criteria decision-making","authors":"Ziyu Chen ,&nbsp;Naijie Chai ,&nbsp;Jianqiang Wang ,&nbsp;Xiaokang Wang","doi":"10.1016/j.ipm.2025.104308","DOIUrl":"10.1016/j.ipm.2025.104308","url":null,"abstract":"<div><div>Restaurant selection has become a complex decision-making process for consumers, driven by an overwhelming volume of online reviews. While text and numerical reviews provide valuable insights, the increasing use of visual content, further enriches consumer evaluations. However, existing research lacks effective methods for integrating multimodal reviews to facilitate informed decision-making. To address this gap, this paper proposes a novel approach for restaurant selection based on multimodal online reviews, the contributions of which mainly focus on the following aspects: (i) employ image captioning techniques to convert image review into textual descriptions, bridging the gap between image and text, (ii) apply text analysis methods to extract relevant evaluation criteria from both text and image-generated descriptions, and (iii) integrate insights from both modalities by assessing the object and content consistency between image and text, ensuring the reliability of reviews. The method is applied to Yelp, using a dataset of 31,412 reviews from 10 restaurants. Eight evaluation criteria are extracted from both text and image reviews. The results show that compared with single-modal and dual-modal review-based recommendation methods, the proposed multimodal approach uncovers more comprehensive evaluation criteria and generates more realistic ranking results. Additionally, the proposed information fusion method outperforms traditional fusion methods in effectively integrating multimodal information.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104308"},"PeriodicalIF":7.4,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144662444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PVSTrans: Patch-view-shape progressive interaction transformer for 3D shape recognition","authors":"Xiangyu Ma,&nbsp;Jing Bai,&nbsp;Zenghui Su,&nbsp;Yubin Wang","doi":"10.1016/j.ipm.2025.104279","DOIUrl":"10.1016/j.ipm.2025.104279","url":null,"abstract":"<div><div>3D shape recognition has made substantial progress due to its wide-ranging applications and increasing research interest. Existing studies have investigated the paradigm of aggregating 3D shape descriptors derived from independently extracted view features. However, this stepwise approach has not fully capitalized on the intrinsic correlations between local regions of varying granularity and global shapes. To address this gap, we propose the Patch-View-Shape Progressive Interaction Transformer (PVSTrans), which enhances shape-patch interactions through progressive view-patch and shape-view interactions, effectively capturing essential dependencies among intra-view features, inter-view features, and global 3D shape features. Furthermore, by utilizing the byproducts of the progressive interaction process, specifically the attention weights of views and intra-view patches, we introduce a Shape-Guided Patch Selection strategy to dynamically identify significant patches in each view, which in conjunction with the multi-view features, forms a more informative 3D shape descriptors for final classification. Experimental results across diverse datasets, including ModelNet40, ScanObjectNN, FG3D, and ShapeNet Core55, demonstrate the effectiveness and generalizability of PVSTrans in 3D shape recognition tasks. Additionally, comprehensive experiments involving various views with differing quantities and spatial relations highlight the robustness of PVSTrans in handling incomplete views and irregular spatial configurations, showcasing its substantial potential for application in complex real-world scenarios. The code is available on <span><span>https://github.com/Oli-lab-nun/PVSTrans</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104279"},"PeriodicalIF":7.4,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144662443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Network dismantling with community-based edge percolation","authors":"Min Wu ,&nbsp;Bitao Dai ,&nbsp;Wu Shi ,&nbsp;Jianhong Mou ,&nbsp;Suoyi Tan ,&nbsp;Stefano Boccaletti ,&nbsp;Xin Lu","doi":"10.1016/j.ipm.2025.104295","DOIUrl":"10.1016/j.ipm.2025.104295","url":null,"abstract":"<div><div>Traditional node-based dismantling strategies, which remove nodes along with their associated edges, tend to incur high costs. In contrast, edge-based strategies are more cost-effective but often suffer from low efficiency due to the large number of edges in most networks. To address these challenges, we propose a divide-and-conquer framework that reinterprets network-level dismantling as cluster-level dismantling. Specifically, we integrate community detection with explosive percolation to develop the Community-based Edge Percolation (CEP) algorithm, which targets critical edges whose removal effectively breaks the network into subcritical components, thereby optimizing dismantling efficiency while minimizing costs. Experiments on 38 synthetic networks derived from four different models, as well as on nine empirical networks, show that CEP consistently outperforms state-of-the-art (SOTA) algorithms across nearly all datasets, yielding improvements of up to 30.611 % in <span><math><msub><mi>f</mi><mi>c</mi></msub></math></span> and 67.108 % in Schneider <em>R</em>. Further analysis indicates that the sets of removed edges identified by CEP have a low correlation with those identified by other benchmarks, underlining its novelty and superior capability in identifying critical edges. Overall, we propose a universal and efficient edge dismantling framework that exhibits substantial advantages in large-scale empirical networks, offering valuable insights into network robustness.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104295"},"PeriodicalIF":7.4,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144662442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated rhetorical move and step recognition in fact-checking articles with neural models","authors":"Xinxue Liu ,&nbsp;Ningyuan Song ,&nbsp;Kejun Chen ,&nbsp;Ye Chen ,&nbsp;Lei Pei","doi":"10.1016/j.ipm.2025.104293","DOIUrl":"10.1016/j.ipm.2025.104293","url":null,"abstract":"<div><div>As online misinformation has drawn social concerns, extensive efforts have been dedicated to fact-checking, which can help contain the spread of misinformation. Among them, persuasive fact-checking articles play a fundamental role, but little work has focused on their discourse structures that are important for understanding how they work. Rhetorical moves and steps, common in genre analysis, can be used to figure out text structures and communicative goals. Based on existing literature, this research first summarizes a rhetorical structure comprising five moves and six steps for fact-checking articles, which describes how they are organized to achieve the persuasive purpose. We then produce a corpus including 420 articles with annotations of our structures. For automated recognition, we propose our BiLSTM with Hierarchical Attention model, which achieves micro-F1 scores of 70 % and 61.5 % for moves and steps, respectively. The performance and subsequent ablation study demonstrate the effectiveness of our model. Utilizing it, an analysis of the distribution and patterns of moves and steps is conducted on an expanded set of 3800 fact-checking articles. Accordingly, we find that the distributions of rhetorical structures in articles have common characteristics and unique differences, reflecting the strategies used when writing. We further conducted sequence mining, and the obtained frequent sequences can help improve fact-checking writing and provide new ideas for studying the relationship between fact-checking texts and their persuasive effects. Generally, the fact-checking rhetorical structures and the automated model proposed in this work have the potential to help leverage the fact-checking corpus and finally contribute to rebutting misinformation.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 6","pages":"Article 104293"},"PeriodicalIF":7.4,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144655654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LLM-Enhanced Multi-Task Joint Learning Model for Misinformation Detection","authors":"Gang Ren ,&nbsp;Li Jiang ,&nbsp;Tingting Huang ,&nbsp;Ying Yang ,&nbsp;Ruida Xie","doi":"10.1016/j.ipm.2025.104305","DOIUrl":"10.1016/j.ipm.2025.104305","url":null,"abstract":"<div><div>The coexistence of Human-Generated Content (HGC) and Artificial Intelligence-Generated Content (AIGC) versions of the same event on social media presents significant challenges for governmental governance and information regulation. In this study, we propose a Large Language Model-enhanced Multi-Task Joint Learning Model for Misinformation Detection (LMTMD) to address the challenge of mixed HGC and AIGC on social media. We design a two-stage instruction, leveraging large language models (LLMs) for data augmentation to generate AIGC versions of events. Furthermore, a novel unsupervised joint learning strategy is proposed, which incorporates content consistency contrastive learning and difference consistency learning. The strategy aims to preserve both the consistency of event content and the heterogeneity between AIGC and HGC. Extensive experiments conducted on real-world datasets, including Weibo and GossipCop, demonstrate that the proposed model outperforms state-of-the-art baselines, achieving a Consistent Match Accuracy (CM-Acc) of 77.21% on the Weibo dataset and 78.13% on the GossipCop dataset. Additionally, the model achieves AIGC detection accuracy rates of 90.58% on the Weibo dataset and 90.95% on the GossipCop dataset, thereby validating the effectiveness of both the model and the joint learning strategy. Our model can effectively adapt to the emerging scenario of mixed HGC and AIGC versions of events on social platforms and enriches the research perspective of misinformation detection.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 6","pages":"Article 104305"},"PeriodicalIF":7.4,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144655653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TEDRec: Transformer-based scientific collaborator recommendation via textual-edge dynamic network modeling","authors":"Keqin Guan ,&nbsp;Weiye Huang ,&nbsp;Ting Chen ,&nbsp;Wai Kin (Victor) Chan","doi":"10.1016/j.ipm.2025.104283","DOIUrl":"10.1016/j.ipm.2025.104283","url":null,"abstract":"<div><div>In academia, scientific cooperation enhances the quality of research and strengthens scholars’ profiles. However, the information overload in the big data era poses challenges in recommending suitable collaborators for scholars or projects. Most existing collaborator recommendation methods prioritize structural dependencies and neglect the temporal details and semantic information. In this study, we leverage the Transformer’s self-attention mechanism to develop a novel academic collaborator recommendation framework using the textual-edge dynamic network called TEDRec. It comprehensively analyzes the collaboration network through three key aspects (i.e., temporality, textual edges, and structural relationships) to learn more valuable author representations, thereby providing scholars with the most suitable partners for future research or projects. Subsequently, several empirical experiments are conducted on three constructed datasets to evaluate their effectiveness. The results validate that the proposed framework does achieve superb performance over baseline models across all evaluation metrics, indicating excellent generalization and robustness.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 6","pages":"Article 104283"},"PeriodicalIF":7.4,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144655655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A method for noise-suppressed multimodal feature integration in urban scene detection","authors":"Xue-juan Han ,&nbsp;Zhong Qu ,&nbsp;Shu-fang Xia","doi":"10.1016/j.ipm.2025.104290","DOIUrl":"10.1016/j.ipm.2025.104290","url":null,"abstract":"<div><div>The complementary imaging properties of visible and thermal infrared make them play a crucial role in multimodal object detection. Multimodal fusion methods that do not effectively deal with intra-modal and inter-modal noise interference can lead to degraded detection performance. To address this problem, we propose a generic multimodal object detection architecture. The noise within the input feature modality is first weakened by the Noise Suppression and Score-guided Fusion module (NSSFuse), while the intra-modal and inter-modal feature representations are enriched, thus facilitating the global interaction of multimodal features. Then the multimodal low-frequency features and high-frequency features are efficiently fused by the Multimodal Frequency Fusion module (MutiFreqFuse), which retains the key information while suppressing the inter-modal irrelevant noise to further enhance the multimodal feature fusion. Numerous experimental results validate the superiority of the model on the benchmark datasets, Multi-Modal Multi-Feature for Traffic Detection (M3FD) and Forward-Looking InfraRed (FLIR). The mean Average Precision (<em>mAP</em>) improves by 4.4–6.8% over the baseline models and is up to 6.3% higher than that of the most recent multimodal models.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 6","pages":"Article 104290"},"PeriodicalIF":7.4,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144655641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}