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 >> Library Science Subjects: Computer Science >> Computer Application Technology submitted time 2016-04-12
Abstract：Open Access academic paper has become important measures of the world's leading countries which promote knowledge sharing, collaborative open innovation, economic growth and inclusive development. Moreover, Open Sharing of academic papers founded by public funding projects has become the consensus of the world’s leading countries, and an important requirement is to deposit those papers in the open access IRs which are attribute to funder and authors’ institute. But the situation of institutional repository in China is serious, such as poorer deposit awareness, incomplete or incorrect submitted data and so on. It affects the development and perfection of China Open Access and open sharing mechanism. Though RJ-Broker can assist and promote to solve problems above, it is mainly related to European PMC data and located abroad. In order to better solve those problems, National Science Library of CAS, as a leader institute of this study in China, with hundreds of Research institutes of Chinese Academy of Sciences as demonstration, and reference to the OA-RJ model, constructed a pushing and routing services of Chinese academic papers, namely iSwitch, implementing automatic deposit. It can help institutes and funders to construct their IRs effectively and promote academic papers utilization by others openly. After iSwitch service is released publicly, it has routed more than 360,000 paper metadata pushed by Web of Science and some experimental Open Access paper data from other publishers to CAS IRs. Now it is a stable service to exchange WOS update data and other publisher data. Besides, with the help of iSwitch, Web of Science has linked full-text link of CAS IR papers since 27, July, 2015.
Peer Review Status:Awaiting Review
Hits
Hits
Downloads
Comment