User Reading Preference and Community Detection in an Online Reading Community

Abstract

To reveal the subject preference of reading and the diversity of reading interest of users in online reading communities, this paper crawls the data of Douban reading, uses the common reading relationship to construct the book networks, and combines the complex network theory and machine learning methods to study the book networks. We find that in the book networks, the two-way weights between disciplines are nearly equal. Users who read philosophy, political science, and other humanities and social sciences have the most extensive interest in reading, while users who read engineering technology disciplines such as mining engineering and nuclear science and technology have the narrowest interest in reading. The network constructed by the secondary disciplines has three distinct communities, corresponding to the three major areas of humanities and social sciences, engineering technology, and basic sciences. For the suitability of interdisciplinary research, the basic sciences are the highest, the humanities and social sciences are the second, and the engineering technology is the lowest. Research results are of great significance to interdisciplinary cross recommendation of books.