Comparative analysis of book tags: a cross-lingual perspective

Abstract

Purpose In the era of social media, users all over the world annotate books with social tags to express their preferences and interests. The purpose of this paper is to explore different tagging behaviours by analysing the book tags in different languages. Design/methodology/approach This investigation collected nearly 56,000 tags of 1,200 books from one Chinese and two English online bookmarking systems; it combined content analysis and machine-processing methods to evaluate the similarities and differences between different tagging systems from a cross-lingual perspective. Jaccard’s coefficient was adopted to evaluate the similarity level. Findings The results show that the similarity between mono-lingual tags of the same books is higher than that of cross-lingual tags in different systems and the similarity between tags of books written for specialties is higher than that of books written for the general public. Research limitations/implications Those who have more in common annotate books with more similar tags. The similarity between users in tagging systems determines the similarity of the tag sets. Practical implications The results and conclusion of this study will benefit users’ cross-lingual information retrieval and cross-lingual book recommendation for online bookmarking systems. Originality/value This study may be one of the first to compare cross-lingual tags. Its methodology can be applied to tag comparison between any two languages. The insights of this study will help develop cross-lingual tagging systems and improve information retrieval.