Subjects: Computer Science >> Computer Application Technology Subjects: Library Science，Information Science >> Information Science submitted time 2023-05-12
Abstract： [Purpose/significance] With the continuous development and change of Large Language Models (LLMs) represented by ChatGPT, classical scenarios in many fields have been given new opportunities. At the same time, more and more researchers begin to focus on how to apply the intelligentness and technology of LLMs to existing scenarios, and analyze the challenges and opportunities brought by these technologies. [Method/process] This is the first time that LLM technology has been introduced into user book rating prediction, which is a typical application scenario in library and information science. We explored the feasibility of using LLM technology in user book rating by building a CUBR (ChatGPT-based model for User Book Rating Prediction) model based on ChatGPT. At the same time, this paper compares different evaluation schemes based on book rating task with existing classical recommendation models, discusses and gives the advantages and disadvantages of CUBR in predicting scenarios of user book scoring, and analyses the possible application opportunities of subsequent LLMs in other scenarios of book recommendation. [Result/conclusion] The experimental research in this paper shows that: (1) CUBR model can achieve good recommendation results on existing user book rating prediction tasks, especially when the target information to be recommended is less, such as one-shot, which performs close to or exceeds the current classical recommendation algorithm, and has strong generalization ability, which is suitable for cold-start recommendation. (2) With the increase of sample content prompted by a single user (e.g. from One-shot to Ten-shot), the predictive effect of CUBR will be significantly improved, indicating that CUBR has good real-time in-context learning ability. [Limitations] The scenarios studied in this paper are limited to the understanding and recommendation of users’ book scoring preferences. In the future, we will try to apply and transform the existing large language model technology in more library and information science scenarios, and achieve better landing effects.
Peer Review Status:
Awaiting Review
Subjects: Library Science，Information Science >> Philology submitted time 2020-05-28
Abstract： [Purposes] A comprehensive understanding of the degree of open access (OA) of academic journals in physics, and the quality of OA papers. Exploring the quality-evaluation methods based on cited OA papers. [Methods] Using statistical principles and bibliometrics methods, 348 physics journals in web of science (WoS), were studied, according to their number of papers and citation collected within 2 years. A comparison and correlation analysis of 9 indicators of about OA proportion of which including OA paper, OA journals, citation of OA paper, as well as acceptability of OA journals, were carried out for the whole physics discipline and 8 branch areas. [Findings] There are 39 OA journals in the whole discipline, accounting for 11.21% of the total journals. The total opening rate and citation rate of OA papers are 28.37% and 35.95%, respectively. The contribution of OA journals to the opening rate and citation rate is 30% and 23.99%, respectively. The opening percentage of high cited papers is 41.87%, and its contribution percentage for citation is 40.56%. OA papers were cited as 4.35 per paper. In eight branch areas, the intervals of mean value of Journals Acceptability (JA) of their journals and OA journals, are {962,301} and {1032,50} respectively. [Conclusions] Empirical analysis shows that : 1)The majority of OA papers come from hybrid- journals. For condensed matter physic, its OA level is much less than the scale of its journal publish. Regarding the OA tactics of high- cited papers, we did not find that they were priority, neither biased. Therefore, increasing the percentage of open access of high- cited papers can be a strategy to improve the quality of OA. 2) OA ratio of Journals and papers , as well the contribution ratio of OA journals can be used as an evaluation index for the degree of openness. The citation ratio of OA papers, the OA ratio of high cited papers, and the average citation per paper in OA journals can be used as indexes for evaluating the quality of OA. 3) The publication volume (PV)of OA journal and the percentile of the journal’s PV can be used for the journal acceptability analysis. "
Peer Review Status:Awaiting Review
Subjects: Library Science，Information Science >> Utilization of Information submitted time 2019-06-27
Abstract： This paper expounds the value orientation and essential connotation of knowledge service in the new information and knowledge environment, and its significance to the transformation of university libraries. This paper analyzes the essential difference between knowledge service and ubiquitous subject service from the perspective of university libraries, and the barriers that university libraries should break through in terms of cognition, theory and practice in order to carry out knowledge services more deeply. It is pointed out that knowledge product is an important form of knowledge service, and the level of knowledge product is the direct embodiment of the library's core value and ability. In addition, this paper gives a clear and systematic explanation and description of the concepts, attributes, types and production principles of knowledge products from a theoretical point of view.
Peer Review Status:Awaiting Review
Hits
Hits
Downloads
Comment