Page 134 - Journal of Library Science in China, Vol.45, 2019

ZHANG Chengzhi, LI Zhuo, ZHAO Mengyuan, LIU Jiahao & ZHOU Qingqing / Citing behavior of Chinese books based on citation content 133

behaviors and disciplinary differences of Chinese books from the perspectives of citation
locations, citation intensities, citation lengths and citation sentiments. The statistical results
showed that: 1) When citing Chinese books, the proportions of Introduction and Related Work
were higher. Literatures in Medicine focused on citations in the Discussion section, while
computer science focused on the Methodology section. 2) The citation lengths about Chinese
books were concentrated between 20 and 160 strings, and the distributions are similar in different
disciplines. 3) Citation intensities were mainly within 3. 4) Most citation sentiments were neutral,
and authors were more inclined to express positive sentiments than negative sentiments when
citing books.
There were still some shortcomings in our research on citation behaviors on Chinese books.
In the process of data collection, there were limitations in completeness and scale of corpus
construction, as full texts of some citing literatures cannot be collected. In addition, regarding
citation content analysis, we only conducted frequency statistics about citation locations,
lengths and intensities, and analysis methods were shallow. In the follow-up study, we will
expand discipline categories and increase the number of books, use technologies of machine
learning and natural language processing, and combine theories and methods of scientometrics
to analyze citation content information at the semantic level such as citation sentiments,
citation functions, citation motivations, etc. We will conduct a more extensive and in-depth
exploration of citation behaviors on books to provide references for scientific evaluation of
books.

Reference

Abu-Jbara, A., Ezra, J., & Radev, D. (2013). Purpose and polarity of citation: Towards NLP based
bibliometrics. In Proceedings of the 2013 Conference of the North American Chapter of the Association for
Computational Linguistics: Human Language Technologies (NAACL-HLT 2013) (pp.596-606). Atlanta,
Georgia: ACL.
Athar, A. (2011). Sentiment analysis of citations using sentence structure-based features. In Proceedings of the
Conference of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language
Technologies (ACL-HLT 2011) (pp.81-87). Portland, Oregon, USA: ACL.
Athar, A., & Teufel, S. (2012). Context-enhanced citation sentiment detection. In Proceedings of the 2012
Conference of the North American Chapter of the Association for Computational Linguistics: Human
Language Technologies (NAACL HLT 2012) (pp.597-601). Montréal, Canada: ACL.
Bertin, M., & Atanassova, I. (2016). Weak links and strong meaning: The complex phenomenon of negational
citations. In Proceedings of BIR 2016 Workshop on Bibliometric-enhanced Information Retrieval (pp.14-
25). Padova, Italy: ACM.
Carletta, J. (1996). Assessing agreement on classification tasks: The kappa statistic. Computational
Linguistics, 22 (21), 249-254.
Catalini, C., Lacetera, N., & Oettl, A. (2015). The incidence and role of negative citations in science. Proc
Natl Acad Sci USA, 112 (45), 13823-13826.
Ding, Y., Zhang, G., Chambers, T., Song, M., Wang, X., & Zhai, C. (2014). Content-based citation