Pub Date : 2024-10-09DOI: 10.1016/j.ipm.2024.103911
Yi-Kun Tang , Heyan Huang , Xuewen Shi , Xian-Ling Mao
Discovering intricate dependencies between topics in topic modeling is challenging due to the noisy and incomplete nature of real-world data and the inherent complexity of topic dependency relationships. In practice, certain basic dependency relationships have been manually annotated and can serve as valuable knowledge resources, enhancing the learning of topic dependencies. To this end, we propose a novel topic model, called Knowledge-Inspired Dependency-Aware Dirichlet Neural Topic Model (KDNTM). Specifically, we first propose Dependency-Aware Dirichlet Neural Topic Model (DepDirNTM), which can discover semantically coherent topics and complex dependencies between these topics from textual data. Then, we propose three methods to leverage accessible external dependency knowledge under the framework of DepDirNTM to enhance the discovery of topic dependencies. Extensive experiments on real-world corpora demonstrate that our models outperform 12 state-of-the-art baselines in terms of topic quality and multi-labeled text classification in most cases, achieving up to a 14% improvement in topic quality over the best baseline. Visualizations of the learned dependency relationships further highlight the benefits of integrating external knowledge, confirming its substantial impact on the effectiveness of topic modeling.
{"title":"Bridging insight gaps in topic dependency discovery with a knowledge-inspired topic model","authors":"Yi-Kun Tang , Heyan Huang , Xuewen Shi , Xian-Ling Mao","doi":"10.1016/j.ipm.2024.103911","DOIUrl":"10.1016/j.ipm.2024.103911","url":null,"abstract":"<div><div>Discovering intricate dependencies between topics in topic modeling is challenging due to the noisy and incomplete nature of real-world data and the inherent complexity of topic dependency relationships. In practice, certain basic dependency relationships have been manually annotated and can serve as valuable knowledge resources, enhancing the learning of topic dependencies. To this end, we propose a novel topic model, called Knowledge-Inspired Dependency-Aware Dirichlet Neural Topic Model (KDNTM). Specifically, we first propose Dependency-Aware Dirichlet Neural Topic Model (DepDirNTM), which can discover semantically coherent topics and complex dependencies between these topics from textual data. Then, we propose three methods to leverage accessible external dependency knowledge under the framework of DepDirNTM to enhance the discovery of topic dependencies. Extensive experiments on real-world corpora demonstrate that our models outperform 12 state-of-the-art baselines in terms of topic quality and multi-labeled text classification in most cases, achieving up to a 14% improvement in topic quality over the best baseline. Visualizations of the learned dependency relationships further highlight the benefits of integrating external knowledge, confirming its substantial impact on the effectiveness of topic modeling.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103911"},"PeriodicalIF":7.4,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417982","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}
Pub Date : 2024-10-09DOI: 10.1016/j.ipm.2024.103916
Qingfeng Zeng , Li Lin , Rui Jiang , Weiyu Huang , Dijia Lin
The proliferation of fraud in online shopping has accompanied the development of e-commerce, leading to substantial economic losses, and affecting consumer trust in online shopping. However, few studies have focused on fraud detection in e-commerce due to its diversity and dynamism. In this work, we conduct a feature set specifically for e-commerce payment fraud, around transactions, user behavior, and account relevance. We propose a novel comprehensive model called Neural Network Based Ensemble Learning with Generation (NNEnsLeG) for fraud detection. In this model, ensemble learning, data generation, and parameter-passing are designed to cope with extreme data imbalance, overfitting, and simulating the dynamics of fraud patterns. We evaluate the model performance in e-commerce payment fraud detection with >310,000 pieces of e-commerce account data. Then we verify the effectiveness of the model design and feature engineering through ablation experiments, and validate the generalization ability of the model in other payment fraud scenarios. The experimental results show that NNEnsLeG outperforms all the benchmarks and proves the effectiveness of generative data and parameter-passing design, presenting the practical application of the NNEnsLeG model in e-commerce payment fraud detection.
{"title":"NNEnsLeG: A novel approach for e-commerce payment fraud detection using ensemble learning and neural networks","authors":"Qingfeng Zeng , Li Lin , Rui Jiang , Weiyu Huang , Dijia Lin","doi":"10.1016/j.ipm.2024.103916","DOIUrl":"10.1016/j.ipm.2024.103916","url":null,"abstract":"<div><div>The proliferation of fraud in online shopping has accompanied the development of e-commerce, leading to substantial economic losses, and affecting consumer trust in online shopping. However, few studies have focused on fraud detection in e-commerce due to its diversity and dynamism. In this work, we conduct a feature set specifically for e-commerce payment fraud, around transactions, user behavior, and account relevance. We propose a novel comprehensive model called Neural Network Based Ensemble Learning with Generation (NNEnsLeG) for fraud detection. In this model, ensemble learning, data generation, and parameter-passing are designed to cope with extreme data imbalance, overfitting, and simulating the dynamics of fraud patterns. We evaluate the model performance in e-commerce payment fraud detection with >310,000 pieces of e-commerce account data. Then we verify the effectiveness of the model design and feature engineering through ablation experiments, and validate the generalization ability of the model in other payment fraud scenarios. The experimental results show that NNEnsLeG outperforms all the benchmarks and proves the effectiveness of generative data and parameter-passing design, presenting the practical application of the NNEnsLeG model in e-commerce payment fraud detection.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103916"},"PeriodicalIF":7.4,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417979","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}
Pub Date : 2024-10-09DOI: 10.1016/j.ipm.2024.103908
Runzhe Zhang , Xiang Yu , Ben Zhang , Qinglan Ren , Yakun Ji
Emerging technologies provide competitive opportunities for latecomers to catch up with leading giants. As most of the extant literature indicated, types of single-dimensional relations from patent data have been revealed in technology opportunity discovery (TOD) research. Still, few have been aware of the more complex characteristics extracted from higher-dimensional patent information such as the patentee-technology relation. To derive this valuable relation for more robust results, this article introduces a novel TOD method, utilizing a recursive graph neural network (RGNN) to transform this high-dimensional information into measures of heterogeneity as internal capability, and combining it with external challenges evaluated by the competitiveness index, to identify technological opportunities. Taking the self-driving vehicle (SDV) industry with 33,347 patent families from 2010 to 2021 as the initial dataset, it shows significant performance promotions compared to previous analogous TOD models. Meanwhile, tested by recent filing patent data, the predicted opportunities are consistent with Huawei and other enterprises. Upon illuminating the intense technological competition situation among the preeminent SDV firms worldwide as a case exploration, this research contributes theoretical and practical views to the TOD research and network analysis.
新兴技术为后来者提供了赶超领先巨头的竞争机会。正如大多数现有文献所指出的，技术机会发现（TOD）研究已经揭示了专利数据中的单维度关系类型。然而，很少有人注意到从专利信息中提取的更复杂的特征，如专利与技术的关系。为了从这一有价值的关系中得出更稳健的结果，本文介绍了一种新颖的 TOD 方法，利用递归图神经网络（RGNN）将这些高维信息转化为衡量内部能力的异质性指标，并将其与竞争力指数评估的外部挑战相结合，从而发现技术机遇。以 2010 年至 2021 年自动驾驶汽车（SDV）行业的 33347 项专利族为初始数据集，与以往类似的 TOD 模型相比，其性能有显著提升。同时，通过近期申请专利数据的检验，其预测的机会与华为等企业一致。本研究以案例探索的方式揭示了全球知名 SDV 企业之间激烈的技术竞争态势，为 TOD 研究和网络分析贡献了理论和实践观点。
{"title":"Discovering technology opportunities of latecomers based on RGNN and patent data: The example of Huawei in self-driving vehicle industry","authors":"Runzhe Zhang , Xiang Yu , Ben Zhang , Qinglan Ren , Yakun Ji","doi":"10.1016/j.ipm.2024.103908","DOIUrl":"10.1016/j.ipm.2024.103908","url":null,"abstract":"<div><div>Emerging technologies provide competitive opportunities for latecomers to catch up with leading giants. As most of the extant literature indicated, types of single-dimensional relations from patent data have been revealed in technology opportunity discovery (TOD) research. Still, few have been aware of the more complex characteristics extracted from higher-dimensional patent information such as the patentee-technology relation. To derive this valuable relation for more robust results, this article introduces a novel TOD method, utilizing a recursive graph neural network (RGNN) to transform this high-dimensional information into measures of heterogeneity as internal capability, and combining it with external challenges evaluated by the competitiveness index, to identify technological opportunities. Taking the self-driving vehicle (SDV) industry with 33,347 patent families from 2010 to 2021 as the initial dataset, it shows significant performance promotions compared to previous analogous TOD models. Meanwhile, tested by recent filing patent data, the predicted opportunities are consistent with Huawei and other enterprises. Upon illuminating the intense technological competition situation among the preeminent SDV firms worldwide as a case exploration, this research contributes theoretical and practical views to the TOD research and network analysis.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103908"},"PeriodicalIF":7.4,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417980","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}
Pub Date : 2024-10-01DOI: 10.1016/j.ipm.2024.103914
Ju Chen , Jun Feng , Shenyu Zhang , Xiaodong Li , Hamza Djigal
Truth inference in crowdsourcing, which studies how to aggregate noisy and biased annotations from workers with varied expertise, is a fundamental technology powering the quality of crowdsourced annotations. Generally, confusion-matrix-based methods are more promising and worker better, as they model each worker’s ability using a confusion matrix rather than a single real value. However, the imbalanced classes and the insufficient training data caused by the pattern ( refers to the number of classes) are still two major issues for the learning of confusion matrices, which call for a robust modeling structure of workers’ confusion matrices. In this article, we propose in response a Fine-Grained Bayesian Classifier Combination model (FGBCC), in which a combination of univariate Gaussian distributions and the standard softmax function is exploited with an aim to improve the estimation of workers’ abilities. Compared to existing methods, FGBCC is capable of learning extensive worker behaviors and is less susceptible to these issues that previous methods suffer from, owing to its stronger generalization ability. Moreover, Considering the exact solution to the complex posterior is unavailable, we devise a computationally efficient algorithm to approximate the posterior. Extensive experiments on 24 real-world datasets covering a wide range of domains, verify the clear advantages of FGBCC over 11 state-of-the-art benchmark methods.
{"title":"Robust annotation aggregation in crowdsourcing via enhanced worker ability modeling","authors":"Ju Chen , Jun Feng , Shenyu Zhang , Xiaodong Li , Hamza Djigal","doi":"10.1016/j.ipm.2024.103914","DOIUrl":"10.1016/j.ipm.2024.103914","url":null,"abstract":"<div><div>Truth inference in crowdsourcing, which studies how to aggregate noisy and biased annotations from workers with varied expertise, is a fundamental technology powering the quality of crowdsourced annotations. Generally, confusion-matrix-based methods are more promising and worker better, as they model each worker’s ability using a confusion matrix rather than a single real value. However, the imbalanced classes and the insufficient training data caused by the <span><math><mrow><mi>K</mi><mo>×</mo><mi>K</mi></mrow></math></span> pattern (<span><math><mi>K</mi></math></span> refers to the number of classes) are still two major issues for the learning of confusion matrices, which call for a robust modeling structure of workers’ confusion matrices. In this article, we propose in response a Fine-Grained Bayesian Classifier Combination model (FGBCC), in which a combination of <span><math><mi>K</mi></math></span> univariate Gaussian distributions and the standard softmax function is exploited with an aim to improve the estimation of workers’ abilities. Compared to existing methods, FGBCC is capable of learning extensive worker behaviors and is less susceptible to these issues that previous methods suffer from, owing to its stronger generalization ability. Moreover, Considering the exact solution to the complex posterior is unavailable, we devise a computationally efficient algorithm to approximate the posterior. Extensive experiments on 24 real-world datasets covering a wide range of domains, verify the clear advantages of FGBCC over 11 state-of-the-art benchmark methods.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103914"},"PeriodicalIF":7.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417978","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}
Pub Date : 2024-10-01DOI: 10.1016/j.ipm.2024.103903
Qing Li, Guanzhong Wu
Temporal knowledge graph reasoning (TKGR) has been considered as a crucial task for modeling the evolving knowledge, aiming to infer the unknown connections between entities at specific times. Traditional TKGR methods try to aggregate structural information between entities and evolve representations of entities over distinct snapshots, while some other methods attempt to extract temporal logic rules from historical interactions. However, these methods fail to address the continuously emerging unseen entities over time and ignore the historical dependencies between entities and relations. To overcome these limitations, we propose a novel method, termed TPNet, which introduces historical information completion strategy (HICS) and pre-trained language model (PLM) to conduct explainable inductive reasoning over TKGs. Specifically, TPNet extracts reliable temporal logical paths from historical subgraphs using a temporal-correlated search strategy. For unseen entities, we utilize HICS to sample or generate paths to supplement their historical information. Besides, a PLM and a time-aware encoder are introduced to jointly encode the temporal paths, thereby comprehensively capturing dependencies between entities and relations. Moreover, the semantic similarity between the query quadruples and the extracted paths is evaluated to simultaneously optimize the representations of entities and relations. Extensive experiments on entity and relation prediction tasks are conducted to evaluate the performance of TPNet. The experimental results on four benchmark datasets demonstrate the superiority of TPNet over state-of-the-art TKGR methods, achieving improvements of 14.35%, 23.08%, 6.75% and 5.38% on MRR, respectively.
{"title":"Explainable reasoning over temporal knowledge graphs by pre-trained language model","authors":"Qing Li, Guanzhong Wu","doi":"10.1016/j.ipm.2024.103903","DOIUrl":"10.1016/j.ipm.2024.103903","url":null,"abstract":"<div><div>Temporal knowledge graph reasoning (TKGR) has been considered as a crucial task for modeling the evolving knowledge, aiming to infer the unknown connections between entities at specific times. Traditional TKGR methods try to aggregate structural information between entities and evolve representations of entities over distinct snapshots, while some other methods attempt to extract temporal logic rules from historical interactions. However, these methods fail to address the continuously emerging unseen entities over time and ignore the historical dependencies between entities and relations. To overcome these limitations, we propose a novel method, termed TPNet, which introduces historical information completion strategy (HICS) and pre-trained language model (PLM) to conduct explainable inductive reasoning over TKGs. Specifically, TPNet extracts reliable temporal logical paths from historical subgraphs using a temporal-correlated search strategy. For unseen entities, we utilize HICS to sample or generate paths to supplement their historical information. Besides, a PLM and a time-aware encoder are introduced to jointly encode the temporal paths, thereby comprehensively capturing dependencies between entities and relations. Moreover, the semantic similarity between the query quadruples and the extracted paths is evaluated to simultaneously optimize the representations of entities and relations. Extensive experiments on entity and relation prediction tasks are conducted to evaluate the performance of TPNet. The experimental results on four benchmark datasets demonstrate the superiority of TPNet over state-of-the-art TKGR methods, achieving improvements of 14.35%, 23.08%, 6.75% and 5.38% on MRR, respectively.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103903"},"PeriodicalIF":7.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418002","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}
Pub Date : 2024-10-01DOI: 10.1016/j.ipm.2024.103906
Qizhi Chen , Hong Yao , Diange Zhou
The fact-condition statements are of great significance in scientific text, via which the natural phenomenon and its precondition are detailly recorded. In previous study, the extraction of fact-condition statement and their relation (super relation) from scientific text is designed as a pipeline that the fact-condition statement and super relation are extracted successively, which leads to the error propagation and lowers the accuracy. To solve this problem, the table filling method is firstly adopted for joint extraction of fact-condition statement and super relation, and the Biaffine Convolution Neural Network model (BCNN) is proposed to complete the task. In the BCNN, the pretrained language model and Biaffine Neural Network work as the encoder, while the Convolution Neural Network is added into the model as the decoder that enhances the local semantic information. Benefiting from the local semantic enhancement, the BCNN achieves the best F1 score with different pretrained language models in comparison with other baselines. Its F1 scores in GeothCF (geological text) reach 73.17% and 71.04% with BERT and SciBERT as pretrained language model, respectively. Moreover, the local semantic enhancement also increases its training efficiency, via which the tags’ distribution can be more easily learned by the model. Besides, the BCNN trained with GeothCF also exhibits the best performance in BioCF (biomedical text), which indicates that it can be widely applied for the information extraction in all scientific domains. Finally, the geological fact-condition knowledge graph is built with BCNN, showing a new pipeline for construction of scientific fact-condition knowledge graph.
{"title":"The joint extraction of fact-condition statement and super relation in scientific text with table filling method","authors":"Qizhi Chen , Hong Yao , Diange Zhou","doi":"10.1016/j.ipm.2024.103906","DOIUrl":"10.1016/j.ipm.2024.103906","url":null,"abstract":"<div><div>The fact-condition statements are of great significance in scientific text, via which the natural phenomenon and its precondition are detailly recorded. In previous study, the extraction of fact-condition statement and their relation (super relation) from scientific text is designed as a pipeline that the fact-condition statement and super relation are extracted successively, which leads to the error propagation and lowers the accuracy. To solve this problem, the table filling method is firstly adopted for joint extraction of fact-condition statement and super relation, and the Biaffine Convolution Neural Network model (BCNN) is proposed to complete the task. In the BCNN, the pretrained language model and Biaffine Neural Network work as the encoder, while the Convolution Neural Network is added into the model as the decoder that enhances the local semantic information. Benefiting from the local semantic enhancement, the BCNN achieves the best F1 score with different pretrained language models in comparison with other baselines. Its F1 scores in GeothCF (geological text) reach 73.17% and 71.04% with BERT and SciBERT as pretrained language model, respectively. Moreover, the local semantic enhancement also increases its training efficiency, via which the tags’ distribution can be more easily learned by the model. Besides, the BCNN trained with GeothCF also exhibits the best performance in BioCF (biomedical text), which indicates that it can be widely applied for the information extraction in all scientific domains. Finally, the geological fact-condition knowledge graph is built with BCNN, showing a new pipeline for construction of scientific fact-condition knowledge graph.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103906"},"PeriodicalIF":7.4,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142417752","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}
Pub Date : 2024-09-30DOI: 10.1016/j.ipm.2024.103888
Esraa Odeh , Shakti Singh , Rabeb Mizouni , Hadi Otrok
This work addresses the problem of Last Mile Delivery (LMD) under time-critical and budget-constrained environments. Given the rapid growth of e-commerce worldwide, LMD has become a primary bottleneck to the efficiency of delivery services due to several factors, including travelling distance, service cost, and delivery time. Existing works mainly target optimizing travelled distance and maximizing gained profit; however, they do not consider time-critical and budget-limited tasks. The deployment of UAVs and the development of crowdsourcing platforms have provided a range of solutions to advance performance in LMD frameworks, as they offer many crowdworkers at varying locations ready to perform tasks instead of having a single point of departure. This work proposes a Hybrid, Crowdsourced, Auction-based LMD (HCA-LMD) framework with a dynamic allocation mechanism for optimized delivery of time-sensitive and budget-limited tasks. The proposed framework allocates tasks to workers as soon as they are submitted, given their urgency level and dropoff location, while considering the price, rating, and location of available workers. This work was compared against two benchmarks to assess the framework’s performance in dynamic environments in terms of on-time deliveries, average delay, and profit. Extensive simulation results showed an outstanding performance of the proposed state-of-the-art LMD framework by accomplishing almost 92% on-time deliveries under varying time- and budget-constrained scenarios, outperforming the first benchmark in the on-time allocation rate by fulfiling an additional 24% of the tasks the benchmark failed, with around 50% drop in average delay time and up to x5.8 gained profit when compared against the second benchmark.
{"title":"Crowdsourced auction-based framework for time-critical and budget-constrained last mile delivery","authors":"Esraa Odeh , Shakti Singh , Rabeb Mizouni , Hadi Otrok","doi":"10.1016/j.ipm.2024.103888","DOIUrl":"10.1016/j.ipm.2024.103888","url":null,"abstract":"<div><div>This work addresses the problem of Last Mile Delivery (LMD) under time-critical and budget-constrained environments. Given the rapid growth of e-commerce worldwide, LMD has become a primary bottleneck to the efficiency of delivery services due to several factors, including travelling distance, service cost, and delivery time. Existing works mainly target optimizing travelled distance and maximizing gained profit; however, they do not consider time-critical and budget-limited tasks. The deployment of UAVs and the development of crowdsourcing platforms have provided a range of solutions to advance performance in LMD frameworks, as they offer many crowdworkers at varying locations ready to perform tasks instead of having a single point of departure. This work proposes a Hybrid, Crowdsourced, Auction-based LMD (HCA-LMD) framework with a dynamic allocation mechanism for optimized delivery of time-sensitive and budget-limited tasks. The proposed framework allocates tasks to workers as soon as they are submitted, given their urgency level and dropoff location, while considering the price, rating, and location of available workers. This work was compared against two benchmarks to assess the framework’s performance in dynamic environments in terms of on-time deliveries, average delay, and profit. Extensive simulation results showed an outstanding performance of the proposed state-of-the-art LMD framework by accomplishing almost 92% on-time deliveries under varying time- and budget-constrained scenarios, outperforming the first benchmark in the on-time allocation rate by fulfiling an additional 24% of the tasks the benchmark failed, with around 50% drop in average delay time and up to x5.8 gained profit when compared against the second benchmark.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103888"},"PeriodicalIF":7.4,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142356984","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}
Pub Date : 2024-09-29DOI: 10.1016/j.ipm.2024.103913
Xiaoyu Li , Shaoyang Guo , Jin Wu , Chanjin Zheng
As a fundamental task of intelligent education, deep learning-based cognitive diagnostic models (CDMs) have been introduced to effectively model dichotomous testing data. However, it remains a challenge to model the polytomous data within the deep-learning framework. This paper proposed a novel Polytomous Cognitive Diagnosis Framework (PCDF), which employs Cumulative Category Response Function (CCRF) theory to partition and consolidate data, thereby enabling existing cognitive diagnostic models to seamlessly analyze graded response data. By combining the proposed PCDF with IRT, MIRT, NCDM, KaNCD, and ICDM, extensive experiments were complemented by data re-encoding techniques on the four real-world graded scoring datasets, along with baseline methods such as linear-split, one-vs-all, and random. The results suggest that when combined with existing CDMs, PCDF outperforms the baseline models in terms of prediction. Additionally, we showcase the interpretability of examinee ability and item parameters through the utilization of PCDF.
{"title":"An interpretable polytomous cognitive diagnosis framework for predicting examinee performance","authors":"Xiaoyu Li , Shaoyang Guo , Jin Wu , Chanjin Zheng","doi":"10.1016/j.ipm.2024.103913","DOIUrl":"10.1016/j.ipm.2024.103913","url":null,"abstract":"<div><div>As a fundamental task of intelligent education, deep learning-based cognitive diagnostic models (CDMs) have been introduced to effectively model dichotomous testing data. However, it remains a challenge to model the polytomous data within the deep-learning framework. This paper proposed a novel <strong>P</strong>olytomous <strong>C</strong>ognitive <strong>D</strong>iagnosis <strong>F</strong>ramework (PCDF), which employs <strong>C</strong>umulative <strong>C</strong>ategory <strong>R</strong>esponse <strong>F</strong>unction (CCRF) theory to partition and consolidate data, thereby enabling existing cognitive diagnostic models to seamlessly analyze graded response data. By combining the proposed PCDF with IRT, MIRT, NCDM, KaNCD, and ICDM, extensive experiments were complemented by data re-encoding techniques on the four real-world graded scoring datasets, along with baseline methods such as linear-split, one-vs-all, and random. The results suggest that when combined with existing CDMs, PCDF outperforms the baseline models in terms of prediction. Additionally, we showcase the interpretability of examinee ability and item parameters through the utilization of PCDF.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103913"},"PeriodicalIF":7.4,"publicationDate":"2024-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142356982","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}
Pub Date : 2024-09-29DOI: 10.1016/j.ipm.2024.103891
Qiao Li, Yuelin Li, Shuhan Zhang, Xin Zhou, Zhengyuan Pan
Intelligent Information Services (IIS) employ Artificial Intelligence (AI)-based systems to provide information that matches the user's needs in diverse and evolving environments. Acknowledging the importance of users in AI-empowered IIS success, a growing number of researchers are investigating AI-empowered IIS from a user-centric perspective, establishing the foundation for a new research domain called “Human-Centered Intelligent Information Services” (HCIIS). Nonetheless, a review of user studies in AI-empowered IIS is still lacking, impeding the development of a clear definition and research framework for the HCIIS field. To fill this gap, this study conducts a systematic review of 116 user studies in AI-empowered IIS. Results reveal two primary research themes in user studies in AI-empowered IIS: human-IIS interaction (including user experience, system quality, user attitude, intention and behavior, information quality, and individual task performance) and IIS ethics (e.g., explainability and interpretability, privacy and safety, and inclusivity). Analyzing research gaps within these topics, this study formulates an HCIIS research framework consisting of three interconnected elements: human values and needs, environment, and service. The interconnections between each pair of elements identify three key research domains in HCIIS: interaction, ethics, and evolution. Interaction pertains to the facilitation of human-IIS interaction to meet human needs, encompassing topics including human-centered theory, evaluation, and the design of AI-empowered IIS interaction. Ethics emphasize ensuring AI-empowered IIS alignment with human values and norms within specific environments, covering topics like general and context-specific AI-empowered IIS ethical principles, risk assessment, and governance strategies. Evolution focuses on addressing the fulfillment of human needs in diverse and dynamic environments by continually evolving intelligence, involving the enhancement of AI-empowered IIS environmental sensitivity and adaptability within an intelligent ecosystem driven by technology integration. Central to HCIIS is co-creation, situated at the intersection of interaction, evolution, and ethics, emphasizing collaborative information creation between IIS and humans through hybrid intelligence. In conclusion, HCIIS is defined as a field centered on information co-creation between IIS and humans, distinguishing it from IIS, which focuses on providing information to humans.
{"title":"A theoretical framework for human-centered intelligent information services: A systematic review","authors":"Qiao Li, Yuelin Li, Shuhan Zhang, Xin Zhou, Zhengyuan Pan","doi":"10.1016/j.ipm.2024.103891","DOIUrl":"10.1016/j.ipm.2024.103891","url":null,"abstract":"<div><div>Intelligent Information Services (IIS) employ Artificial Intelligence (AI)-based systems to provide information that matches the user's needs in diverse and evolving environments. Acknowledging the importance of users in AI-empowered IIS success, a growing number of researchers are investigating AI-empowered IIS from a user-centric perspective, establishing the foundation for a new research domain called “Human-Centered Intelligent Information Services” (HCIIS). Nonetheless, a review of user studies in AI-empowered IIS is still lacking, impeding the development of a clear definition and research framework for the HCIIS field. To fill this gap, this study conducts a systematic review of 116 user studies in AI-empowered IIS. Results reveal two primary research themes in user studies in AI-empowered IIS: human-IIS interaction (including user experience, system quality, user attitude, intention and behavior, information quality, and individual task performance) and IIS ethics (e.g., explainability and interpretability, privacy and safety, and inclusivity). Analyzing research gaps within these topics, this study formulates an HCIIS research framework consisting of three interconnected elements: human values and needs, environment, and service. The interconnections between each pair of elements identify three key research domains in HCIIS: interaction, ethics, and evolution. Interaction pertains to the facilitation of human-IIS interaction to meet human needs, encompassing topics including human-centered theory, evaluation, and the design of AI-empowered IIS interaction. Ethics emphasize ensuring AI-empowered IIS alignment with human values and norms within specific environments, covering topics like general and context-specific AI-empowered IIS ethical principles, risk assessment, and governance strategies. Evolution focuses on addressing the fulfillment of human needs in diverse and dynamic environments by continually evolving intelligence, involving the enhancement of AI-empowered IIS environmental sensitivity and adaptability within an intelligent ecosystem driven by technology integration. Central to HCIIS is co-creation, situated at the intersection of interaction, evolution, and ethics, emphasizing collaborative information creation between IIS and humans through hybrid intelligence. In conclusion, HCIIS is defined as a field centered on information co-creation between IIS and humans, distinguishing it from IIS, which focuses on providing information to humans.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103891"},"PeriodicalIF":7.4,"publicationDate":"2024-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142356983","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}
Pub Date : 2024-09-28DOI: 10.1016/j.ipm.2024.103902
Yinlong Xiao , Zongcheng Ji , Jianqiang Li , Qing Zhu
Recently, lexicon-enhanced methods for Chinese Named Entity Recognition (NER) have achieved great success which requires a high-quality lexicon. However, for the domain-specific Chinese NER, it is challenging to obtain such a high-quality lexicon due to the different distribution between the general lexicon and domain-specific data, and the high construction cost of the domain lexicon. To address these challenges, we introduce dual-source lexicons (i.e., a general lexicon and a domain lexicon) to acquire enriched lexical knowledge. Considering that the general lexicon often contains more noise compared to its domain counterparts, we further propose a dual-stream model, Dual Flat-LAttice Transformer (DualFLAT), designed to mitigate the impact of noise originating from the general lexicon while comprehensively harnessing the knowledge contained within the dual-source lexicons. Experimental results on three public domain-specific Chinese NER datasets (i.e., News, Novel and E-commerce) demonstrate that our method consistently outperforms the single-source lexicon-enhanced approaches, achieving state-of-the-art results. Specifically, our proposed DualFLAT model consistently outperforms the baseline FLAT, with an increase of up to 1.52%, 4.84% and 1.34% in F1 score for the News, Novel and E-commerce datasets, respectively.
最近，用于中文命名实体识别（NER）的词典增强方法取得了巨大成功，这需要高质量的词典。然而，对于特定领域的中文 NER，由于通用词库和特定领域数据的分布不同，以及领域词库的构建成本较高，要获得这样一个高质量的词库具有挑战性。为了应对这些挑战，我们引入了双源词典（即通用词典和领域词典）来获取丰富的词汇知识。考虑到与领域词库相比，通用词库通常包含更多噪声，我们进一步提出了一种双流模型--双扁平阶梯转换器（Dual Flat-LAttice Transformer，DualFLAT），旨在减轻来自通用词库的噪声的影响，同时全面利用双源词库中包含的知识。在三个公共领域特定中文 NER 数据集（即新闻、小说和电子商务）上的实验结果表明，我们的方法始终优于单源词典增强方法，取得了最先进的结果。具体来说，我们提出的 DualFLAT 模型始终优于基线 FLAT，在新闻、小说和电子商务数据集上的 F1 分数分别提高了 1.52%、4.84% 和 1.34%。
{"title":"DualFLAT: Dual Flat-Lattice Transformer for domain-specific Chinese named entity recognition","authors":"Yinlong Xiao , Zongcheng Ji , Jianqiang Li , Qing Zhu","doi":"10.1016/j.ipm.2024.103902","DOIUrl":"10.1016/j.ipm.2024.103902","url":null,"abstract":"<div><div>Recently, lexicon-enhanced methods for Chinese Named Entity Recognition (NER) have achieved great success which requires a high-quality lexicon. However, for the domain-specific Chinese NER, it is challenging to obtain such a high-quality lexicon due to the different distribution between the general lexicon and domain-specific data, and the high construction cost of the domain lexicon. To address these challenges, we introduce dual-source lexicons (<em>i.e.,</em> a general lexicon and a domain lexicon) to acquire enriched lexical knowledge. Considering that the general lexicon often contains more noise compared to its domain counterparts, we further propose a dual-stream model, Dual Flat-LAttice Transformer (DualFLAT), designed to mitigate the impact of noise originating from the general lexicon while comprehensively harnessing the knowledge contained within the dual-source lexicons. Experimental results on three public domain-specific Chinese NER datasets (<em>i.e.,</em> News, Novel and E-commerce) demonstrate that our method consistently outperforms the single-source lexicon-enhanced approaches, achieving state-of-the-art results. Specifically, our proposed DualFLAT model consistently outperforms the baseline FLAT, with an increase of up to 1.52%, 4.84% and 1.34% in F1 score for the News, Novel and E-commerce datasets, respectively.</div></div>","PeriodicalId":50365,"journal":{"name":"Information Processing & Management","volume":"62 1","pages":"Article 103902"},"PeriodicalIF":7.4,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142356981","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号