Recommender System for Scholarly Articles to Monitor COVID-19 Trends in Social Media Based on Low-Cost Topic Modeling
Abstract
During the last years, many computer systems have been developed to track and monitor COVID-19 social network interactions. However, these systems have been mainly based on robust probabilistic approaches like Latent Dirichlet Allocation (LDA). In another context, health recommender systems have always been personalized to the needs of single users instead of regional communities. Such applications will not be useful in the context of a public health emergency such as COVID-19 where general insights about local populations are needed by health policy makers to solve critical issues in a timely basis. In this research paper, we propose to modify LDA by letting it be driven by knowledge resources and we demonstrate how we can apply our topic modeling method to local social network interactions about COVID-19 to generate precise topic clusters reflecting the social trends about the pandemic at a low cost. Then, we outline how terms in every topic cluster can be converted into a search query to generate scholarly publications from PubMed Central for adjusting COVID-19 trendy thoughts in a population.
Houcemeddine Turki
Medical student
My research interests include the development of a large-scale framework for using open resources and semantic technologies for driving biomedical informatics and research evaluation at a low cost.
Mohamed Ali Hadj Taieb
Assistant professor
My research interests include semantic similarity, semantic relatedness, knowledge representation, Big Data, social media, data management systems and graph embedding.
Mohamed Ben Aouicha
Associate professor
My research interests concern information retrieval, semantic technologies, social media analytics, knowledge representation, Big Data and graph embedding.