Wenjing Pian , Ruinan Zheng , Jianxing Chi , Christopher S.G. Khoo
{"title":"Enhancing public campaign messages: The power of causal arguments","authors":"Wenjing Pian , Ruinan Zheng , Jianxing Chi , Christopher S.G. Khoo","doi":"10.1016/j.ipm.2025.104160","DOIUrl":"10.1016/j.ipm.2025.104160","url":null,"abstract":"<div><div>Campaign messages are often issued by government and international agencies to persuade the public to adopt certain standpoints or take actions related to public issues. However, there is a paucity of empirical research investigating how to improve the messages to increase adoption—from an information and argumentation perspective. This study developed a model of public campaign message adoption based on an argumentation perspective and the information adoption model, and investigated how different types of causal argument elements contribute to the adoption intention of public campaign messages. Two within-subject online experiments with fictitious and real scenarios were conducted, and Bayesian hierarchical modeling that treated participant and scenario as random factors were employed in the data analysis. The results indicate that two types of argument support elements (i.e., support to the data and support to the bridging premise) significantly increased the adoption intention of campaign messages in different scenarios. Additionally, the argument support to the bridging premise exhibited a bigger effect than the support to the data. Finally, their effects on adoption intention were fully mediated by perceived argument strength and source credibility of the campaign messages. This study sheds light on how to design more persuasive campaign messages related to public issues.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104160"},"PeriodicalIF":7.4,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724092","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":"Diff-GNDCRec: A diffusion model with graph-node enhancement and difference comparison for recommendation","authors":"Xiulan Hao , Xinwei Li , Yunliang Jiang","doi":"10.1016/j.ipm.2025.104154","DOIUrl":"10.1016/j.ipm.2025.104154","url":null,"abstract":"<div><div>Attention mechanism is widely used by Graph Neural Networks (GNNs) based recommender systems. However, data sparsity and noise can potentially disrupt the model, and consistence information within the graph structure may not fully capture the relative importance of graph nodes, which could influence the result of classification. Therefore, a <strong><u>diff</u></strong>usion model with <strong><u>g</u></strong>raph-<strong><u>n</u></strong>ode enhancement and <strong><u>d</u></strong>ifference <strong><u>c</u></strong>omparison for <strong><u>rec</u></strong>ommendation (Diff-GNDCRec) is proposed. Firstly, the feature vectors of the graph nodes are processed by Graph Convolutional Network (GCN) to obtain feature embedding, which is subsequently augmented by introducing Gaussian noise via a diffusion model. Secondly, augmented views of the graph nodes are generated through a multi-head Graph Attention Network (GAT) and denoised using average pooling to recover user interactions effectively. Finally, to better reflect the importance of the nodes, the model assigns weights to the nodes based on the neighborhood characteristics and combines the consistence and difference metrics to form the forward-supervised signals and contrast-supervised signals, respectively, and integrates them to improve the contrast learning effect. The model autonomously learns complex relationships between nodes, improving both recommendation accuracy and the model’s generalization capability in a fuzzy environment. Comparative evaluations with eleven benchmark models across three real-world datasets—Tmall, Amazon, and Gowalla—demonstrate that Diff-GNDCRec improves recall and normalized discounted cumulative gain by 1.26% to 3.32% and 1.37% to 4.12%, respectively. These results demonstrate the effect of Diff-GNDCRec.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104154"},"PeriodicalIF":7.4,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735247","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":"Pure profit-oriented continuous influence maximization considering cost budget: A gradient descent-based approach","authors":"Wei Liu , Ziwei Deng , Yixin Chen , Ling Chen","doi":"10.1016/j.ipm.2025.104172","DOIUrl":"10.1016/j.ipm.2025.104172","url":null,"abstract":"<div><div>Continuous influence maximization (CIM) has been commonly applied in online viral marketing. To maximize the sales revenue, CIM assigns each user a continuous weight reflecting the likelihood and cost for him becoming a seed. Most of the existing studies on CIM aim to maximize the revenue from the sale of products, but do not pay attention to its net profit, which is the revenue minus the cost of promotion. However, in real-world marketing, the fundamental goal of business is to maximize net profit, rather than simply maximizing sales revenue. Moreover, traditional CIM assumes a budget to limit the total cost of all users. This assumption does not tenable in practical applications. In practice, it is not necessary to incur costs for all the users. Instead, the budget should be set only for the cost associated with the seed set. In this paper, an extended CIM problem of budget-constrained cost distribution for profit maximization (BCDPM) is defined. BCDPM aims to maximize the expected net profit by assigning different costs to the customers according to their ability to spread influence of the product, ensuring that the cost of each potential seed set does not exceed the budget. We prove the NP-hardness of BCDPM and the non-monotonicity and non-modularity of its objective function. By formulating the BCDPM problem into a constrained optimization, we present a gradient descent-based algorithm to determine the optimal cost distribution for this problem. An algorithm is presented to compute the gradient for maximizing the increment of profit in each iteration of the gradient descent. To avoid the time-consuming simulations, we design an effective algorithm to get the largest profit increment of each seed set. Experiment results on real and synthetic networks show that the proposed algorithm can obtain much larger expected net profit than other algorithms.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104172"},"PeriodicalIF":7.4,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724407","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}
Longzhu He , Peng Tang , Yuanhe Zhang , Pengpeng Zhou , Sen Su
{"title":"Mitigating privacy risks in Retrieval-Augmented Generation via locally private entity perturbation","authors":"Longzhu He , Peng Tang , Yuanhe Zhang , Pengpeng Zhou , Sen Su","doi":"10.1016/j.ipm.2025.104150","DOIUrl":"10.1016/j.ipm.2025.104150","url":null,"abstract":"<div><div>Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating relevant information from external sources to produce more accurate outputs. However, in contexts involving sensitive data, such as healthcare, RAG systems can introduce significant privacy risks, potentially causing the exposure of private information. In this paper, we introduce LPRAG (<u>L</u>ocally <u>P</u>rivate <u>R</u>etrieval-<u>A</u>ugmented <u>G</u>eneration), a privacy-preserving RAG framework with formal privacy guarantees based on local differential privacy (LDP). LPRAG aims to augment LLM responses using perturbed data to protect privacy. The key insight of LPRAG is to achieve privacy preservation by applying LDP perturbation to private entities within the text (rather than the entire text). Specifically, LPRAG first identifies various types of private entities (words, numbers, or phrases) in texts and assigns privacy budgets based on an adaptive privacy budget assignment strategy. It then perturbs these entities using different LDP perturbation mechanisms designed for words, numbers, or phrases. Finally, the RAG system enhances LLM responses based on the perturbed texts. Extensive experimental results demonstrate that our approach maintains satisfactory utility with low privacy loss.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104150"},"PeriodicalIF":7.4,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724281","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}
Pedro Henrique Silva Rodrigues , Daniel Xavier de Sousa , Celso França , Gestefane Rabbi , Thierson Couto Rosa , Marcos André Gonçalves
{"title":"Risk-sensitive optimization of neural deep learning ranking models with applications in ad-hoc retrieval and recommender systems","authors":"Pedro Henrique Silva Rodrigues , Daniel Xavier de Sousa , Celso França , Gestefane Rabbi , Thierson Couto Rosa , Marcos André Gonçalves","doi":"10.1016/j.ipm.2025.104126","DOIUrl":"10.1016/j.ipm.2025.104126","url":null,"abstract":"<div><div>We answer open research questions regarding the (hard) problem of incorporating risk-sensitiveness measures into Deep Neural Networks for ranking models of retrieval and recommender systems. Risk-sensitive measures are important for controlling the bias towards the average when optimizing ranking solutions’ effectiveness. In previous work, we proposed the <em>RiskLoss</em> function which presents two important adaptations for neural network ranking in ad-hoc retrieval: a differentiable loss function and the use of networks’ sub-portions, obtained via dropout, as baseline systems for optimizing risk sensitiveness. However, questions remained to be answered regarding the generality, cost, and applicability of our solution. In this article, we respond to these questions by (i) applying <em>RiskLoss</em> to ranking in recommender systems, (ii) analyzing the execution cost of <em>RiskLoss</em> and (iii) providing an experimental evaluation of <em>RiskLoss</em>’ resilience to overfitting. Our experiments, comparing seven loss functions on three benchmark recommendation datasets (AIV, ML35M, ML25M, ML100K and ML1M) and four Learning To Rank datasets (WEB30K, WEB10K, YAHOO and MQ2007), with thousands to millions of interactions, reveal that <em>RiskLoss</em> presents the most consistent risk sensitiveness behavior, with gains up to 4.5% in GeoRisk@10 without significant losses in effectiveness. In particular, <em>RiskLoss</em> can reduce the number of bad recommendations by over 11% for “hard to recommend” users. We also show that <em>RiskLoss</em> is not much affected by overfitting.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104126"},"PeriodicalIF":7.4,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724408","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":"VoxT-GNN: A 3D object detection approach from point cloud based on voxel-level transformer and graph neural network","authors":"Qiangwen Zheng , Sheng Wu , Jinghui Wei","doi":"10.1016/j.ipm.2025.104155","DOIUrl":"10.1016/j.ipm.2025.104155","url":null,"abstract":"<div><div>Recently, a variety of LiDAR-based methods for the 3D detection of single-class objects, large objects, or in straightforward scenes have exhibited competitive performance. However, their detection performance in complex scenarios with multi - sized and multi - class objects is limited. We observe that the core problem leading to this phenomenon is the insufficient feature learning of small objects in point clouds, making it difficult to obtain more discriminative features. To address this challenge, we propose a 3D object detection framework based on point clouds that takes into account the detection of small objects, termed VoxT-GNN. The framework comprises two core components: a Voxel-Level Transformer (VoxelFormer) for local feature learning and a Graph Neural Network Feed-Forward Network (GnnFFN) for global feature learning. By embedding GnnFFN as an intermediate layer between the encoder and decoder of VoxelFormer, we achieve flexible scaling of the global receptive field while maximally preserving the original point cloud structure. This design enables effective adaptation to objects of varying sizes and categories, providing a viable solution for detection applications across diverse scenarios. Extensive experiments on KITTI and Waymo Open Dataset (WOD) demonstrate the strong competitiveness of our method, particularly showing significant improvements in small object detection. Notably, our approach achieves the second-highest mAP of 65.44% across three categories (car, pedestrian, and cyclist) on KITTI benchmark. The source code is available at <span><span>https://github.com/yujianxinnian/VoxT-GNN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104155"},"PeriodicalIF":7.4,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gang Zhou , Haizhou Wang , Di Jin , Wenxian Wang , Shuyu Jiang , Rui Tang , Xingshu Chen
{"title":"A Toxic Euphemism Detection framework for online social network based on Semantic Contrastive Learning and dual channel knowledge augmentation","authors":"Gang Zhou , Haizhou Wang , Di Jin , Wenxian Wang , Shuyu Jiang , Rui Tang , Xingshu Chen","doi":"10.1016/j.ipm.2025.104143","DOIUrl":"10.1016/j.ipm.2025.104143","url":null,"abstract":"<div><div>For real-time content moderation systems, detecting toxic euphemisms remains a significant challenge due to the lack of available annotated datasets and the ability to deeply identify euphemistic toxicity. In this paper, we proposed the TED-SCL framework (Toxic Euphemism Detection based on Semantic Contrastive Learning) to solve these problems. Firstly, we collected nearly 8 million comments and constructed a toxic euphemism dataset (TE-Dataset), which contains 18,971 comments, covering six topics and 424 PTETs (Potential Toxic Euphemism Terms). Next, we employed contrastive learning to separate toxic euphemism samples from harmless ones in semantic space and enhance the model’s ability to capture subtle differences. Lastly, we utilized a dual channel knowledge augmentation module to integrate background knowledge with toxic comments and improve the identification of toxic euphemisms. Experimental results demonstrate that TED-SCL outperforms existing SOTA in toxic euphemism detection tasks, achieving accuracy of 93.94%, recall of 93.36%, and F1 score of 93.23%. Furthermore, TED-SCL demonstrates better generalization, zero-shot capability, and greater robustness on different topics and datasets, which provides a new way for real-time content moderation systems to detect euphemistic and implicit toxicity effectively.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104143"},"PeriodicalIF":7.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143704120","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}
Shiqi Sun , Kun Zhang , Jingyuan Li , Min Yu , Kun Hou , Yuanzhuo Wang , Xueqi Cheng
{"title":"Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering","authors":"Shiqi Sun , Kun Zhang , Jingyuan Li , Min Yu , Kun Hou , Yuanzhuo Wang , Xueqi Cheng","doi":"10.1016/j.ipm.2025.104147","DOIUrl":"10.1016/j.ipm.2025.104147","url":null,"abstract":"<div><div>In recent research on open-domain question answering (ODQA), significant advances have been achieved by merging document retrieval techniques with large language models (LLMs) to answer questions. However, current ODQA methods present two challenges: the introduction of noise during retrieval and granularity errors during generation. To address these challenges, we propose the Retriever-Generator-Verification (RGV) framework, which consists of the Evidence Document Generator (EDG), the Candidate Entities Generator (CEG), and the Candidate Subgraphs Validator and Ranker (CSVR). EDG combines retrieval and generative mechanisms to construct comprehensive reference documents, ensuring broad coverage of potential answers. CEG then extracts and expands multi-dimensional candidate answer entities from these reference documents, capturing finer-grained information. Finally, CSVR verifies the candidate subgraphs against external knowledge sources and ranks them based on relevance, refining the final answers to enhance their accuracy and reliability. By systematically integrating these components, the RGV framework improves the completeness of retrieved information while effectively mitigating noise during retrieval and granularity errors during generation, thereby enhancing the overall reliability of ODQA. We assessed the efficacy of our method on three widely used datasets, and the experimental results demonstrate that our method exhibits competitive performance in benchmark tests. Compared to the state-of-the-art method, our approach achieves a 2.3% improvement in F1 score on the WebQSP dataset and a 1.3% increase in Hits@1 on the CWQ dataset.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104147"},"PeriodicalIF":7.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143704116","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 scientific table understanding with type-guided chain-of-thought","authors":"Zhen Yin , Shenghua Wang","doi":"10.1016/j.ipm.2025.104159","DOIUrl":"10.1016/j.ipm.2025.104159","url":null,"abstract":"<div><div>Tables in scientific papers convey essential data and insights. Traditional methods struggle with the complexity of modern table data. This study introduces the SciTable-Sowise framework, which utilizes a fine-tuned table classifier to determine the specific type of each table and uses this type information to formulate the Chain-of-Thought (CoT) prompts for large language models (LLMs), significantly enhancing the processing of table content. We constructed the Sci-Table-QA and Sci-Table-Summarization datasets, which comprise 55,000 reasoning QA samples and 5264 summarization samples across multiple disciplines in both Chinese and English. Experimental results show a 7.2 % increase in table reasoning accuracy in Chinese (81.9 %) and a 7.5 % increase in English (83.1 %), surpassing existing models. Our method also enhances summarization performance, as validated by ROUGE, BertScore, and GPT-4o model evaluation metrics (G-Eval-4). This approach demonstrates substantial real-world application potential in scientific research and business analytics, with our datasets publicly available to support future research.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104159"},"PeriodicalIF":7.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143704121","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":"Efficient and explainable sequential recommendation with language model","authors":"Zihao Li, Lixin Zou, Chao Ma, Chenliang Li","doi":"10.1016/j.ipm.2025.104122","DOIUrl":"10.1016/j.ipm.2025.104122","url":null,"abstract":"<div><div>Motivated by the outstanding success of large language models (LLMs) in a broad spectrum of NLP tasks, applying them for explainable recommendation become a cutting-edge recently. However, due to the inherent inconsistency in the information and knowledge focused, most existing solutions treat item recommendation and explanation generation as two distinct processes, incurring extensive computational costs and memory footprint. Besides, these solutions often pay more attention to the item-side (<em>i.e.,</em> item attributes and descriptions) for explanation generation while ignoring the user personalized preference. To close this gap, in this paper, we propose a personalized explainable sequential recommendation model, which aims to output the recommendation results as well as the corresponding personalized explanations via a single inference step. Moreover, to mitigate the substantial computational cost, we devise a rescaling adapter and a Fast Fourier Transform (FFT) adapter for parameter-efficient fine-tuning (PEFT). Theoretical underpinnings and experimental results demonstrate that compared with prevalent PEFT solutions, our adapter possesses three merits: (1) a larger receptive field across the entire sequence for long-term dependency modeling; (2) element product in orthogonal bases for noise attenuation and signal amplifying; (3) better alignment and uniformity properties for precise recommendation. Comprehensive experiments on three public datasets against nine sequential recommendation solutions and three explanation generation solutions illustrate our <span>Pleaser</span> outperforms the strong baselines significantly with only 5% parameter fine-tuning. Code available at <span><span>https://github.com/WHUIR/PLEASER</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 4","pages":"Article 104122"},"PeriodicalIF":7.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143704118","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}