Information Processing & Management最新文献

AlignTime: Interperiodic phase alignment sampling for time-series forecasting 用于时间序列预测的周期间相位对准采样

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-28 DOI: 10.1016/j.ipm.2025.104296

Min Wang , Hua Wang , Fan Zhang

{"title":"AlignTime: Interperiodic phase alignment sampling for time-series forecasting","authors":"Min Wang , Hua Wang , Fan Zhang","doi":"10.1016/j.ipm.2025.104296","DOIUrl":"10.1016/j.ipm.2025.104296","url":null,"abstract":"<div><div>Time-series forecasting is widely applied in various fields to provide decision-making support. However, existing forecasting methods often struggle to capture periodic behavior in nonstationary sequences. When periodic fluctuations exhibit nonstationarity over time, current forecasting architectures can face difficulties in effectively handling dynamic phase shifts across different periods. To address these challenges, we proposed AlignTime — a novel time series forecasting model that revisits forecasting from a downsampling perspective. We treated each period in a time series as an independent analytical unit and considered elements in the same phase to share similar signal properties. By sampling these phase-aligned elements, we constructed a phase subsequence rich in features from different periods, enabling a deeper understanding and utilization of intrinsic periodic patterns. We introduced a method for computing the globally dominant period and performed phase-aligned sampling based on it, effectively aggregating time points in the same phase. We then employed phase-enhanced convolution to extract features from the phase-aligned subsequences, captured dynamic phase shifts between periods, and represented the data in the feature space. Finally, we aggregated the feature subsequences from each phase window to generate the final predictive sequence, fully leveraging the inter-period dynamic phase correlations. We conducted extensive experiments on both long- and short-term forecasting tasks. For long-term forecasting, AlignTime achieves a 6.85% improvement in MSE and a 4.09% improvement in MAE compared to baseline models. For short-term forecasting, over 70% of the results achieve optimal performance, confirming the effectiveness of AlignTime in time-series forecasting tasks. Code is available at: <span><span>https://github.com/xiaoxiaomiwang/AlignTime</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104296"},"PeriodicalIF":7.4,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144714486","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}

引用次数: 0

Incorporating worker rivalry into task recommendations on crowdsourcing platforms: A novel framework for boosting participation and efficiency 将工人竞争纳入众包平台的任务建议：提高参与和效率的新框架

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-27 DOI: 10.1016/j.ipm.2025.104310

Hefu Liu , Wenlong Li , Meng Chen , Juntao Wu

{"title":"Incorporating worker rivalry into task recommendations on crowdsourcing platforms: A novel framework for boosting participation and efficiency","authors":"Hefu Liu , Wenlong Li , Meng Chen , Juntao Wu","doi":"10.1016/j.ipm.2025.104310","DOIUrl":"10.1016/j.ipm.2025.104310","url":null,"abstract":"<div><div>Crowdsourcing platforms have demonstrated significant advantages in addressing complex business and societal challenges. However, their task recommendation systems face dual challenges stemming from information overload and inadequate modeling of competitive relationships. While existing studies primarily utilize collaborative filtering and content-based approaches for task recommendation, these methods typically overlook the systematic impact of dynamic rivalry among workers in open crowdsourcing environments. To address this gap, we propose the Crowdsourcing Task Recommendation model with Competitive Relationships among Workers (CTRCRW), integrating a three-dimensional rivalry modeling mechanism (rivalry-similarity, repeated competition, and evenly matched competition) with deep learning techniques. Specifically, CTRCRW develops a multi-dimensional rivalry quantification approach and introduces a Rivalry Attention Module (RAM), leveraging graph neural networks combined with cosine similarity weights and a learnable gating mechanism to capture explicit competitive behaviors and implicit psychological motivations. Experiments on real-world datasets confirm that CTRCRW significantly improves recommendation accuracy and competitive rationality, effectively reducing workers’ search costs. This study contributes to theory and methodology for relationship-driven recommendations in crowdsourcing, providing generalized insights for resource allocation in complex interactive environments.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104310"},"PeriodicalIF":7.4,"publicationDate":"2025-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713502","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}

引用次数: 0

Social impact of recommendation algorithm in crisis: Forming algorithmic experience through group information interaction and algorithm task fit 危机下推荐算法的社会影响：通过群体信息交互和算法任务拟合形成算法经验

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-26 DOI: 10.1016/j.ipm.2025.104323

Xiwei Wang , Siguleng Wuji , Mali Li , Yutong Liu , Ran Luo

{"title":"Social impact of recommendation algorithm in crisis: Forming algorithmic experience through group information interaction and algorithm task fit","authors":"Xiwei Wang , Siguleng Wuji , Mali Li , Yutong Liu , Ran Luo","doi":"10.1016/j.ipm.2025.104323","DOIUrl":"10.1016/j.ipm.2025.104323","url":null,"abstract":"<div><div>This study explores the societal impact of recommendation algorithms during crisis situations, specifically examining the dynamic interaction between users, algorithms, and tasks in disaster contexts. By integrating the Task-Technology Fit (TTF) model, Stress and Coping theory, and Social Identity theory, the research constructs a comprehensive analytical framework to better understand group information behavior and algorithmic experiences. Addressing the theoretical limitations of existing research that separates human-algorithm interaction from human-human interaction, this study innovatively incorporates algorithmic performance and interaction purpose into a unified analysis model. Through an experimental design, the study manipulates the \"personalized content recommendation\" feature by enabling and disabling it to observe how different algorithm configurations influence user perceptions and behaviors. The findings reveal that a strong task-technology fit enhances group information interaction intentions, with personalized content recommendations playing a dual moderating role. They not only bridge perceived disaster threats and task-technology fit but also impact the relationship between perceived disaster threat, perceived interactive support, and overall algorithm experience. This study contributes to the theoretical expansion of task-technology fit applications in disaster contexts and provides practical insights for designing recommendation algorithms in crisis situations. It highlights the importance of algorithmic forming and contextual fitness in improving public engagement and crisis response efficiency.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104323"},"PeriodicalIF":7.4,"publicationDate":"2025-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711830","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}

引用次数: 0

DiffSBR: A diffusion model for session-based recommendation DiffSBR：基于会话的推荐的扩散模型

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-25 DOI: 10.1016/j.ipm.2025.104284

Zihe Wang , Bo Jin

{"title":"DiffSBR: A diffusion model for session-based recommendation","authors":"Zihe Wang , Bo Jin","doi":"10.1016/j.ipm.2025.104284","DOIUrl":"10.1016/j.ipm.2025.104284","url":null,"abstract":"<div><div>Session-based recommendation (SBR) focuses on recommending items to anonymous users within short interaction sequences. Existing solutions focus on modeling item representations as fixed embedding vectors within the discriminative learning paradigm, which fail to accurately capture the diverse preferences that user exhibit during dynamic decision-making. We argue that users in the anonymous environment can fundamentally be regarded as a <strong>normative implicit group</strong>, exhibiting both <strong>homogeneous preference</strong> and <strong>heterogeneous preference</strong> when selecting items. To tackle this, we propose a Diffusion Model for Session-based Recommendation (DiffSBR). Specifically, we first model the aforementioned user diverse preferences from both local and global views. Next, we introduce a cluster-aware diffusion model, which directly represents heterogeneous preference clusters as distribution through forward and reverse processes, while indirectly influencing homogeneous preference via the attention mechanism in the final prediction stage, thereby improving the learning of item and session representations and enhancing the next-item recommendation. Experimental results show that DiffSBR outperforms the strong baseline, demonstrating that this sampling-allocation approach accurately reflects the uncertainty and variability in user preferences.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104284"},"PeriodicalIF":7.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703791","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}

引用次数: 0

Dual transferable knowledge interaction for source-free domain adaptation 面向无源领域自适应的双重可转移知识交互

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-25 DOI: 10.1016/j.ipm.2025.104302

Mengmeng Zhan , Zongqian Wu , Jiaying Yang , Lin Peng , Jialie Shen , Xiaofeng Zhu

{"title":"Dual transferable knowledge interaction for source-free domain adaptation","authors":"Mengmeng Zhan , Zongqian Wu , Jiaying Yang , Lin Peng , Jialie Shen , Xiaofeng Zhu","doi":"10.1016/j.ipm.2025.104302","DOIUrl":"10.1016/j.ipm.2025.104302","url":null,"abstract":"<div><div>Source-free domain adaptation (SFDA) aims to adapt a pre-trained model to an unlabeled target domain without requiring access to source data, addressing privacy and security concerns in real-world applications. While vision-language models like CLIP have shown promise for SFDA, existing approaches primarily leverage CLIP’s final predictions for adaptation, overlooking its feature-space discriminative insights. This limitation hinders knowledge transfer effectiveness. To bridge this gap, we propose Dual Transferable Knowledge Interaction (DTKI), a novel framework that integrates local feature structures from CLIP with inter-class relationships from the source model to guide adaptation. Specifically, DTKI constructs a nearest-neighbor graph to capture local target domain structures and enhances CLIP’s textual representations using inter-class relationships from the source model’s classifier. Our theoretical analysis demonstrates that these two complementary knowledge transfer mechanisms significantly reduce classification errors. Extensive experiments on four public SFDA benchmarks validate DTKI’s superiority, achieving state-of-the-art performance across multiple domain adaptation scenarios, including partial-set, closed-set, and open-set SFDA.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104302"},"PeriodicalIF":7.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703743","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}

引用次数: 0

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-24 DOI: 10.1016/j.ipm.2025.104311

Jinqing Yang , Xingyu Luo , Ruhan Yang , Zhifeng Liu , Shengzhi Huang

{"title":"How dissimilar synonyms affect the results of experiments based on fine-grained knowledge co-occurrence networks","authors":"Jinqing Yang , Xingyu Luo , Ruhan Yang , Zhifeng Liu , Shengzhi Huang","doi":"10.1016/j.ipm.2025.104311","DOIUrl":"10.1016/j.ipm.2025.104311","url":null,"abstract":"<div><div>Despite efforts to reduce the effects of dissimilar synonyms on the construction of knowledge networks, few researchers have examined the extent to which it affects the results of experiments. In this work, we developed a multi-tiered comparative analysis framework to investigate how the dissimilar synonym issue influences the topology structure and functional dynamics of knowledge networks. Specifically, <em>Pearson</em> correlation analysis was performed to quantify the relationship between topology structure variables in the ontology knowledge network and their counterparts in the raw term-based network. Subsequently, we applied the Levenshtein distance algorithm to assess sequence dissimilarity in the ordinal sequences between variable pairs. Finally, we calculated the difference between the topology variables of the same knowledge node in the two networks. To evaluate the effect of the dissimilar synonym issue, we applied our framework to the scenario of knowledge impact prediction and ranking. The experimental results show that (1) the similarity values of the ordinal sequences of eigenvector centrality, <em>PageRank</em> coefficient, betweenness centrality, and closeness centrality variables are respectively 0.410, 0.404, 0.342, and 0.407, which means the dissimilar synonym issue has a considerable effect on the topology structure calculations of knowledge networks; and (2) higher-ranked knowledge nodes show lower overlap rates between the raw term-based knowledge network and the ontology knowledge network, suggesting that the dissimilar synonym issue influences the reliability of detecting high-impact knowledge. (3) in the scenario of knowledge impact prediction, the dissimilar synonym issue has minimal effect on the task performance.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104311"},"PeriodicalIF":7.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703790","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}

引用次数: 0

Dynamic knowledge correction via abductive for domain question answering 基于溯因的领域问答动态知识纠错

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-24 DOI: 10.1016/j.ipm.2025.104306

Yulin Zhou , Ruizhang Huang , Chuan Lin , Lijuan Liu , Yongbin Qin

引用次数: 0

ConDiff: Conditional graph diffusion model for recommendation ConDiff：推荐的条件图扩散模型

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-24 DOI: 10.1016/j.ipm.2025.104303

Xilin Wen, Xu-Hua Yang, Gang-Feng Ma

{"title":"ConDiff: Conditional graph diffusion model for recommendation","authors":"Xilin Wen, Xu-Hua Yang, Gang-Feng Ma","doi":"10.1016/j.ipm.2025.104303","DOIUrl":"10.1016/j.ipm.2025.104303","url":null,"abstract":"<div><div>Currently, most existing graph diffusion models do not explicitly integrate key features of user collaboration signals and user–item (U–I) interaction graph in recommendation systems, limiting their ability to enhance recommendation performance. To alleviate this limitation, we propose a conditional graph diffusion model for recommendation, named ConDiff. Specifically, we introduce random Gaussian noise during the forward diffusion process to perturb the original graph structure. In the reverse generation process, we design an autoencoder for conditional graph generation, CGG-AE, which: (1) introduces personalized collaboration signals for each user online through logical operation; (2) utilizes user collaboration signals and U–I interaction information as conditional inputs to the diffusion model, obtain diffusion-collaboration and diffusion-interaction data in latent space through the encoder, and then use the decoder to reconstruct and generate higher-quality original U–I interaction information. Extensive experiments on three benchmark datasets demonstrate that ConDiff outperforms state-of-the-art models. Notably, on the Anime dataset, ConDiff improves Recall@10 and Recall@20 by 18.99% and 17.94%, reaching 0.2607 and 0.3721, respectively. The code is available at <span><span>https://github.com/xl-wen/ConDiff</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104303"},"PeriodicalIF":7.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694637","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}

引用次数: 0

A novel framework with ComMAND: A combined method for author name disambiguation 一个带ComMAND的新框架：作者姓名消歧的组合方法

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-23 DOI: 10.1016/j.ipm.2025.104304

Natan S. Rodrigues , Célia G. Ralha

{"title":"A novel framework with ComMAND: A combined method for author name disambiguation","authors":"Natan S. Rodrigues , Célia G. Ralha","doi":"10.1016/j.ipm.2025.104304","DOIUrl":"10.1016/j.ipm.2025.104304","url":null,"abstract":"<div><div>Author Name Disambiguation (AND) in digital bibliographic repositories is a persistent challenge due to homonyms and synonyms, compromising information retrieval and database integrity. This work presents a novel framework with a <strong>Com</strong>bined <strong>M</strong>ethod for <strong>A</strong>uthor <strong>N</strong>ame <strong>D</strong>isambiguation (ComMAND) that integrates transfer learning with SciBERT, Graph Convolutional Network (GCN), and Graph-enhanced Hierarchical Agglomerative Clustering (GHAC) to enhance AND performance. The framework includes a Graphical User Interface (GUI), allowing users to load datasets, execute AND tasks, and visualize results without requiring programming knowledge. By semantically analyzing document content and leveraging graph-based relationships, our approach achieves higher precision in identifying unique authors. Experimental results on AMiner-12, AMiner-18, and DBLP validate the effectiveness of the framework. Considering the DBLP dataset, which contains extensive ambiguous name references (679), the results show the highest F1 of 0.869 and K-metric of 0.972 compared to the baseline works, with improvements ranging from 1.1% to 33.6% over baseline works. These findings highlight the effectiveness of combining machine learning, graph-based techniques, and clustering for large-scale AND tasks.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104304"},"PeriodicalIF":7.4,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686731","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}

引用次数: 0

Considering dual-followers to dynamically model and analyze online rumor propagation 考虑双追随者对网络谣言传播进行动态建模和分析

IF 7.4 1区管理学

Information Processing & Management Pub Date : 2025-07-23 DOI: 10.1016/j.ipm.2025.104301

Shufang Wu , Mengjiao Gao , Jie Zhu

{"title":"Considering dual-followers to dynamically model and analyze online rumor propagation","authors":"Shufang Wu , Mengjiao Gao , Jie Zhu","doi":"10.1016/j.ipm.2025.104301","DOIUrl":"10.1016/j.ipm.2025.104301","url":null,"abstract":"<div><div>Online rumor propagation poses significant challenges to social stability and public security. Previous studies have overlooked the behavioral differences and impacts between active and passive spreaders in the rumor propagation. To address this gap, we propose a novel Dual-Followers–Susceptible–Observer–Infective–Counter–Recovery model (DF-SIOCR), which simultaneously incorporates the followers of rumor-spreading and those of rumor-countering, providing a more fine-grained framework for analyzing online rumor propagation. In the model analysis, we calculate the basic reproduction number, three equilibrium points of the new model, and analyze the stability of these equilibrium points. In the experiments, we analyze the influence of several key parameters on online rumor propagation and conduct simulations on three different network structures to validate the model’s efficacy across diverse social networks. Finally, the comparative experiments are conducted on five public rumor events. Experimental results show that the DF-SIOCR model exhibits superior performance in R-squared, RMSE, and MAE, significantly outperforming existing approaches. These results indicate the model’s high accuracy in predicting rumor propagation trends and strong adaptability to complex dissemination scenarios. This work not only advances theoretical understanding of rumor propagation dynamics but also provides actionable insights for developing effective rumor governance strategies.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"63 1","pages":"Article 104301"},"PeriodicalIF":7.4,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686732","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}

引用次数: 0