Academic Knowledge Sharing In Research Social Network: Two Strategies Recommendation System Design

Academic information overload has presented a challenge to researchers given the rapid growth of scientific articles.Methods have been proposed to help professional readers find relevant articles on the basis of their publications.Although effectively sharing publications is essential to spreading knowledge and ideas,scant studies have focused on knowledge sharing from knowledge providers perspective.In reality,knowledge provider can only share their articles through a few offline channels.A large number of articles can be accessed through search engines,but they are not necessarily shared with knowledge seekers after publication.This scenario leads to the unfortunate phenomenon of many undiscovered papers.The rise of research social networks has provided researchers with a new and effective platform for knowledge sharing and discovery under open access policy.knowledge providers can upload and share their publications with their peers and friends on-line.Few research has studied how to effectively share articles on professional social networks from knowledge providers perspective.The previous research has four limitations:First,the existing research lacks a framework for academic knowledge sharing suitable for research social networks from the perspective of knowledge providers;Second,the previous research on knowledge sharing focused on the internal organization,ignoring the situation on the research social network;Third,the previous recommendation system design was similarity-based only,ignoring the strategic differences in different academic knowledge sharing scenarios;Fourth,the social behaviour data is ignored in the construction of user profile,which leads to insufficient timeliness and accuracy of recommendations;In the research quality dimension,only absolute value is adopted,and the relative quality between disciplines and journals is ignored,which not suitable for the situation of academic knowledge sharing.This study leverages online research social network to propose a general academic knowledge sharing framework to assist authors in effectively sharing their publications with interested readers.Two academic knowledge sharing strategies are developed to meet different demands.For authors who want to share their articles with situations that are particularly similar to their own research,a similarity-based academic knowledge sharing framework is proposed.For authors who want to share their articles with situations that are relevant to their own research but not particularly similar,a relevance-based academic knowledge sharing framework is put forward.In our approach,researcher-level and document-level analyses are integrated in the same model,which works in two stages.1)Researcher-level analysis combines research topic,social relation and research quality dimensions.2)Document-level analysis includes short-term research interests extracted from online social behaviour and long-term research interests drawn from researchers' publications.Our research is developed and verified in ScholarMate,a prevalent research social network platform.Compared with other baseline methods,our approach significantly improves the accuracy and satisfaction of recommendation results.The research in this paper has the following contributions:First this paper designs academic knowledge sharing framework from the perspective of knowledge providers to help them use the recommendation system to effectively share their published papers to potential knowledge seekers,provide a new perspective for subsequent research;Second,the study confirmed that the academic knowledge recommendation system can effectively improve the acceptance rate and satisfaction of knowledge sharing by designing a knowledge sharing recommendation system based on research social networks.Enriched IT system's promotion of knowledge sharing is not limited to passively providing user communication platforms.The intelligent recommendation system can actively promote knowledge sharing,proving its importance in knowledge sharing,and also providing new perspective for designing a smarter system for subsequent knowledge sharing.Third,this paper proposes a general academic knowledge sharing framework suitable for different knowledge sharing strategies.This framework integrates the researcher-level and document-level analysis in same model.It supplements the deficiencies of only one level of analysis in the recommendation system design.Through the two-step framework design can reduce the amount of massive calculations and has the ability to be deployed on large real research social networks.Also,the proposed general academic knowledge sharing framework can be applied to different knowledge sharing strategies and has strong applicability;Fourth,in the specific model design,this paper introduces the relative research quality to effectively solve the mismatch problem.At the document-level analysis,by capturing users' social behaviour data and balancing long-term and short-term research interests,it can effectively solve the cold start problem of new users and improve the performance of the recommendation system.