Classical methods for mapping domain knowledge structures, namely bibliographic coupling (BC) and co-citation (CC) analyses, rely on co-reference or CC counts, which may lack precision and reliability. While full-text mining can enhance BC and CC strength, there is limited comparative analysis on the impact of different full-text citation features. This study explores the optimisation effects of four full-text citation features: citation content, sentiment, position and mention frequency. Enhanced strength algorithms for BC and CC relationships were designed based on these features, and a comparative experiment was conducted in the field of oncology. Deep learning techniques were employed to extract various citation features, which were then used in the proposed models and control groups. These full-text citation features were assessed for their effectiveness and characteristics in discovering domain knowledge structure. The study revealed that including full-text citation features improved the traditional methods, aligning more closely with expert knowledge. These features offered distinct insights but also introduced potential drawbacks. The research results hold insights for gaining a deeper understanding regarding the optimisation effects of full-text citation features on traditional bibliometric methods.
ElkissAShenSFaderA, .et alBlind men and elephants: what do citation summaries tell us about a research article?J Am Soc Inf Sci Technol2008; 59: 51–62.
4.
EdgeD.Why I amnot a co-citationist. Soc Soc Stud Sci Newsl1977; 1977: 13–19.
ZhangRHYuanJP.Enhanced author bibliographic coupling analysis using semantic and syntactic citation information. Scientometrics2022; 127: 7681–7706.
7.
DingYZhangGChambersT.Content-based citation analysis: the next generation of citation analysis. J Assoc Inf Sci Technol2014; 65: 1820–1833.
8.
HuZChenCLiuS.Where are citations located in the body of scientific articles? A study of the distributions of citation locations. J Informetr2013; 7: 887–896.
9.
BertinMAtanassovaIGingrasY, .et alThe invariant distribution of references in scientific articles. J Assoc Inf Sci Technol2015; 67: 164–177.
10.
LuCDingYZhangC.Understanding the impact change of a highly cited article: a content-based citation analysis. Scientometrics2017; 112: 927–945.
11.
ThijsB.Using neural-network based paragraph embeddings for the calculation of within and between document similarities. Scientometrics2020; 125: 835–849.
12.
HouWRLiMNiuDK.Counting citations in texts rather than reference lists to improve the accuracy of assessing scientific contribution. Bioessays2011; 33: 724–727.
13.
DingYLiuXZGuoC, .et alThe distribution of references across texts: some implications for citation analysis. J Informetr2013; 7: 583–592.
14.
LiuSChenC.The differences between latent topics in abstracts and citation contexts of citing papers. J Am Soc Inf Sci Technol2013; 64: 627–639.
15.
DingYSongMHanJ, .et alEntitymetrics: measuring the impact of entities. PLoS ONE2013; 8: e71416.
16.
TeufelSSiddharthanATidharD. Automatic classification of citation function. In: 2006 conference on empirical methods in natural language processing (ed TeufelSSiddharthanATidharD), Sydney, NSW, Australia, 22–23 July 2006, pp. 103–110. Stroudsburg, PA: Association for Computational Linguistics.
17.
AtharA. Sentiment analysis of citations using sentence structure-based features. In: ACL 2011 student session (ed AtharA), Portland, OR, June2011, pp. 81–87. Stroudsburg, PA: Association for Computational Linguistics.
18.
PresterJWagnerGSchryenG, .et alClassifying the ideational impact of information systems review articles: a content-enriched deep learning approach. Decis Support Syst2021; 140: 113432.
19.
IhsanIQadirMA.An NLP-based citation reason analysis using CCRO. Scientometrics2021; 126: 4769–4791.
20.
WangMZhangJJiaoS, .et alImportant citation identification by exploiting the syntactic and contextual information of citations. Scientometrics2020; 125: 2109–2129.
21.
Abu-JbaraARadevD.Reference scope identification in citing sentences. In: 2012 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (ed Abu-JbaraARadevD), Montreal, QC, Canada, 3–8 June 2012, pp. 80–90. Stroudsburg, PA: Association for Computational Linguistics.
22.
AngroshMCranefieldSStangerN. Context identification of sentences in related work sections using a conditional random field: towards intelligent digital libraries. In: 10th annual joint conference on digital libraries (ed AngroshMCranefieldSStangerN), Gold Coast, QLD, Australia, 21–25 June 2010, pp. 293–302. New York: ACM.
23.
MaBWZhangCZWangYZ, .et alEnhancing identification of structure function of academic articles using contextual information. Scientometrics2022; 127: 885–925.
24.
AhmedIAfzalMT.A systematic approach to map the research articles’ sections to IMRAD. IEEE Access2020; 8: 129359–129371.
25.
GippBBeelJ. Identifying related documents for research paper recommender by CPA and COA. In: WCECS 2009: World congress on engineering and computer science, vols I and II (ed GippBBeelJ), San Francisco, CA, 20–22 October 2009, pp. 636–639, https://www.iaeng.org/publication/WCECS2009/WCECS2009_pp636-639.pdf
26.
LiuSChenC.The proximity of co-citation. Scientometrics2012; 91: 495–511.
27.
BoyackKWSmallHKlavansR.Improving the accuracy of co-citation clustering using full text. J Am Soc Inf Sci Technol2013; 64: 1759–1767.
LiuXZhangJGuoC.Full-text citation analysis: a new method to enhance scholarly networks. J Am Soc Inf Sci Technol2013; 64: 1852–1863.
30.
KumarVSendhilkumarSMahalakshmiGS.Author similarity identification using citation context and proximity. In: 2017 second international conference on recent trends and challenges in computational models (ICRTCCM) (ed KumarVSendhilkumarSMahalakshmiGS), Tindivanam, India, 3–4 February 2017, pp. 217–221. New York: IEEE.
31.
HabibRAfzalMT.Sections-based bibliographic coupling for research paper recommendation. Scientometrics2019; 119: 643–656.
32.
KesslerMM.Bibliographic coupling between scientific papers. Am Doc1963; 14: 10–25.
33.
ZhaoDCappelloAJohnstonL.Functions of uni-and multi-citations: implications for weighted citation analysis. J Data Inf Sci2017; 2: 51–69.
34.
HassanSUSafderIAkramA, .et alA novel machine-learning approach to measuring scientific knowledge flows using citation context analysis. Scientometrics2018; 116: 973–996.
35.
SmallH.Cocitation in the scientific literature: A new measure of the relationship between two documents. J Am Soc Inf Sci1973; 24: 265–269.
36.
SmallH.Co-citation context analysis and the structure of paradigms. J Doc1980; 36: 183–196.
37.
LeiSChenHHuangY, .et alResearch on automatic recognition of academic citation context. Libr Inf Serv2016; 60: 78–87.
38.
DevlinJChangMWLeeK, .et alBERT: pre-training of deep bidirectional transformers for language understanding. In: 2019 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT 2019), vol 1 (ed DevlinJChangMWLeeK, et al.), Minneapolis, MN, June 2019, pp. 4171–4186. Stroudsburg, PA: Association for Computational Linguistics.
39.
ReimersNGurevychI.Sentence-BERT: sentence embeddings using siamese BERT-networks. In: 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP 2019) (ed ReimersNGurevychI), Hong Kong, China, 3–7 November 2019, pp. 3982–3992. Stroudsburg, PA: Association for Computational Linguistics.
40.
HernándezMGómezJM. Survey in sentiment, polarity and function analysis of citation. In: Proceedings of the first workshop on argumentation mining (ed HernándezMGómezJM), Baltimore, MD, June 2014, pp. 102–103. Stroudsburg, PA: Association for Computational Linguistics.
41.
NicholsonJMMordauntMLopezP, .et alScite: a smart citation index that displays the context of citations and classifies their intent using deep learning. Quant Sci Stud2021; 2: 882–898.
ZhaoDStrotmannA.Telescopic and panoramic views of library and information science research 2011–2018: a comparison of four weighting schemes for author co-citation analysis. Scientometrics2020; 124: 255–270.
