在线读书社区中的用户阅读偏好及社团发现

User Reading Preference and Community Detection in an Online Reading Community

为了揭示在线读书社区中用户阅读的学科偏好及阅读兴趣的多样性,抓取了豆瓣读书社区的数据,利用用户共同阅读关系构建图书网络,结合复杂网络理论和机器学习方法对网络进行了研究.发现图书网络中,学科之间的双向权重近乎相等;阅读哲学、政治学等人文社科的用户跨学科阅读最为广泛,而阅读矿业工程、核科学与技术等工程科技学科的用户跨学科阅读最窄;二级学科网络具有3个明显的社团,对应人文社科、工程科技和基础科学三大领域,跨学科研究的适合度由高到低依次为基础科学、人文社科和工程科技.研究结果对于图书跨学科交叉推荐具有重要意义.

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.