Inf. Process. Manag.最新文献

How does government microblog affect tourism market value? The perspective of signaling theory 政府微博如何影响旅游市场价值?信号理论的视角

Inf. Process. Manag. Pub Date : 2022-07-01 DOI: 10.1016/j.ipm.2022.102991

Hongzhi Zhu, Fangyun Wang

引用次数: 8

Building for Tomorrow: Assessing the Temporal Persistence of Text Classifiers 为明天而建:评估文本分类器的时间持久性

Inf. Process. Manag. Pub Date : 2022-05-11 DOI: 10.48550/arXiv.2205.05435

Rabab Alkhalifa, E. Kochkina, A. Zubiaga

{"title":"Building for Tomorrow: Assessing the Temporal Persistence of Text Classifiers","authors":"Rabab Alkhalifa, E. Kochkina, A. Zubiaga","doi":"10.48550/arXiv.2205.05435","DOIUrl":"https://doi.org/10.48550/arXiv.2205.05435","url":null,"abstract":"Performance of text classification models tends to drop over time due to changes in data, which limits the lifetime of a pretrained model. Therefore an ability to predict a model's ability to persist over time can help design models that can be effectively used over a longer period of time. In this paper, we provide a thorough discussion into the problem, establish an evaluation setup for the task. We look at this problem from a practical perspective by assessing the ability of a wide range of language models and classification algorithms to persist over time, as well as how dataset characteristics can help predict the temporal stability of different models. We perform longitudinal classification experiments on three datasets spanning between 6 and 19 years, and involving diverse tasks and types of data. By splitting the longitudinal datasets into years, we perform a comprehensive set of experiments by training and testing across data that are different numbers of years apart from each other, both in the past and in the future. This enables a gradual investigation into the impact of the temporal gap between training and test sets on the classification performance, as well as measuring the extent of the persistence over time.","PeriodicalId":203304,"journal":{"name":"Inf. Process. Manag.","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132166385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Contributorship in scientific collaborations: The perspective of contribution-based byline orders 科学合作中的贡献:基于贡献的署名顺序的视角

Inf. Process. Manag. Pub Date : 2022-05-01 DOI: 10.1016/j.ipm.2022.102944

Chao Lu, Chenwei Zhang, Chengrui Xiao, Ying Ding

引用次数: 5

Assessing the effectiveness of a three-way decision-making framework with multiple features in simulating human judgement of opinion classification 评估具有多特征的三方决策框架在模拟人类意见分类判断中的有效性

Inf. Process. Manag. Pub Date : 2022-03-01 DOI: 10.1016/j.ipm.2021.102823

L. Subhashini, Yuefeng Li, Jinglan Zhang, Ajantha S Atukorale

引用次数: 5

Video retrieval framework based on color co-occurrence feature of adaptive low rank extracted keyframes and graph pattern matching 基于自适应低秩提取关键帧颜色共现特征和图形模式匹配的视频检索框架

Inf. Process. Manag. Pub Date : 2022-03-01 DOI: 10.1016/j.ipm.2022.102870

Ajay Kumar Mallick, S. Mukhopadhyay