Subjects: Library Science，Information Science >> Library Science submitted time 2023-07-26 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Identifying expertise tags of scholars is the most critical task in scholar profiling. Expertise tags contribute to finding peer experts, clustering domain scholars and selecting reviewers.[Method/process] This study analyzed related factors on the scholar expertise in academic publications, then constructed a hierarchical analysis model on the weight allocation of the factors. The TextRank algorithm has been used to identify topical terms in Chinese corpus, and the conceptual linking technique in English corpus. The extracted terms, together with the previously analyzed factors have been combined to select the expertise tags of the scholars. In this study, a group of honored scholars of different domains have been selected. Their research expertise information from their resumes have been taken as evaluation benchmark. And the expertise tags extracted from their publications have been compared with the benchmark by human judgment and additional semantic similarity judgment.[Result/conclusion] The evaluation shows that the expertise tags of 71.9% scholars are acceptable for Chinese, and 77.2% for English. The experiment proves that the method proposed in this article is pragmatic and may lead to reasonable results. The chief innovation of this study lies in three aspects, Firstly, term extraction approaches that suit to different application conditions have been explored, such as the language of publication and the availability of domain knowledge base. Secondly, multiple features have been combined together to identify the expertise tags of scholars, including the content of publications, the substantial contribution to the publications of the scholars, and the influence to the domain of the publications. Thirdly, a reasonable experimental design and evaluation method is proposed, and the proposed approach has been verified by combining manual scoring and semantic calculation results.
Subjects: Library Science，Information Science >> Information Science submitted time 2023-04-01 Cooperative journals: 《图书情报工作》
Abstract： [Purpose/significance] Users often faced different levels of information searching difficulties in search. In order to better understand user needs and improve the retrieval system, a concise and effective method was needed to measure the difficulty of searching for information.[Method/process] This study took the cost of effort on time and behavior for queries as manifestation of users' information seeking difficulty. The session type was divided according to the user's behavior pattern in the session, the session type with the least cost and the query requirement was satisfied as the comparison baseline, and the cost of the baseline session was used to measure the difficulty of other session types. In order to optimize the expression model of the cost, the correlation test of the behavioral indicators of the search cost was carried out, and the behavioral characteristics with good independence and discrimination were selected by factor analysis for modeling. Using National Science and Technology Library (NSTL) logs and Sogou logs as data sets to compare the difficulty faced by users in both academic search and general search environments, as well as during the exploration process represented by and different session types.[Result/conclusion] In the two search systems measured in this paper, the information search difficulty faced by users is 2.30 and 1.57 respectively, and the difficulty in academic search is higher than that in general search. In the two sessions that embodied the process of academic exploration, the difficulty levels were 2.35 and 4.13 respectively. The method proposed in this paper can use simple numerical values to summarize the search difficulties with multiple influencing factors, and can be used in different types of sessions and search environments, enriching the evaluation methods of the retrieval system.
Hits
Hits
Downloads
Comment