[Objective] This paper analyzes the citation intentions and sentiments of academic papers on the South China Sea issue, aiming to reveal their citation behaviors and the emerging research ideas. [Methods] First, we used the feature-based SVM algorithm to automatically classify citations. Then, we built a citation classification knowledge map. Finally, we analyzed the papers’ citation characteristics from their overall distribution, national differences, and topics. [Results] The F1 macro average of the automatic classification model reached 0.75 and 0.72 on citation intentions and sentiments. Chinese scholars tend to defend China’s sovereignty over the South China Sea from a historical perspective. Their leading citating intentions are “technical basis” or “backgrounds”, while their citation sentiment is generally “neutral”. [Limitations] The corpus data size and comprehensiveness need to be expanded. [Conclusions] Chinese scholars should strengthen their arguments of the South China Sea issue from the legal perspectives.
齐小英, 李昕尉, 杨海平. 基于意图和情感的南海学术论文引用特征研究*[J]. 数据分析与知识发现, 2022, 6(12): 53-69.
Qi Xiaoying, Li Xinwei, Yang Haiping. Citation Characteristics of Scholarly Articles on South China Sea Based on Intentions and Sentiments. Data Analysis and Knowledge Discovery, 2022, 6(12): 53-69.
While at least one scholar has argued that the South China Sea is not a flash point, this article contends that in the second decade of the twenty-first century, this body of water does indeed meet the criteria.
comparison
negative
10.1080/09557571. 2019.1639622
10.1111/1468- 2346.12657
The English-language literature on the territorial and maritime disputes in the South China Sea is extensive, but much of the recent debate focuses on China’s allegedly assertive behaviour and its “salami-slicing” strategy to change the status quo incrementally in China’s favour.
background
neutral
10.1080/09512748. 2019.1587497
10.1162/ 016228800560543
Defensive realism, focusing on cooperative security strategies for peace (Taliaferro, 2001; Tang, 2010), seems at odds with the impression of Chinese coercion.
technical basis
positive
Table 2 标注样本示例
Fig.2 数据集分布
类别
扩展的线索词
背景
statement, literature, recent, by the end of, in fact, decade, source, historic, announcements, agreements, government official, in retrospect, note, speaking, it is well known that, rules, treaty, widely accepted, research by, emerge, example, state, issued, there have been, noti?cation, statement of claim, provoke, cases, publish, review, argument, reference, date back, endorse
比较
in contrast to, conversely, runs counter to, instead, comparing with, than, shift, among these, most, while, some, others, similarly, similar to, viewed differently, differ from, siding with, against, previously, later, in the past, contrary, vary
依据
proclamation, refer to, clarify, positioning analysis, point, perspective, suggest, assumption, reiterating, emphasis, basic function, point out, denote, summarize, legal basis, observe that, distilled, essentially, based on, based upon, on the basis of, according to, coupled with, given, quote, focused on, plays a significant role in, more importantly, understood as, tied with, key issues, pays due attention to, drawing on, challenge, it can be seen that, state, view, be evident in
acceptable, feasible, reasonable, evident in, significance, much, presumption, clarified, specifically, contributed to, enriched, extensively rooted in, made great strides, enhance, dominant, difficult not to agree with, good illustration, more importantly, contribution, set the foundation on, remind
中性
closely resembles, some argue, others assert, the first, second, many scholars, statement
负向
but, even as, little, however, yet, nevertheless, few, challenge, bare the real possibility, overlook, no consensus on, irony, even as, not necessarily be able to, runs counter to
Table 4 引用情感分类的线索词
Fig.3 不同特征数量下的引用意图分类效果
类别
精确率(P)
召回率(R)
F1值
引用文本数
背景
0.77
0.81
0.79
21
比较
1.00
0.50
0.67
4
依据
0.75
0.68
0.71
31
使用
0.79
0.85
0.81
52
准确率
0.78
108
宏平均
0.83
0.71
0.75
108
加权平均
0.78
0.78
0.78
108
Table 5 引用意图测试集分类结果
Fig.4 不同特征数量下的引用情感分类效果
类别
精确率(P)
召回率(R)
F1值
引文文本数
正向
0.66
0.74
0.70
42
中性
0.81
0.77
0.79
62
负向
1.00
0.50
0.67
4
准确率
0.75
108
宏平均
0.82
0.67
0.72
108
加权平均
0.76
0.75
0.75
108
Table 6 引用情感测试集分类结果
句子
抽取的特征(部分)
引用 意图
引用情感
词性标注
线索词
时态
The effect is similar in the South China Sea, where a weakening of coastal upwelling leads to decreased fish abundance, especially when ENSO warming is amplified by secular increases in global mean temperatures.
DT NN VBZ JJ IN DT NP NP NP WRB DT NN IN JJ NN VVZ TO VVN NN NN RB WRB NP NN VBZ VVN IN JJ NNS IN JJ JJ NNS SENT
'is' 'similar' 'is'
present
technical basis
neutral
In contrast, everyday nationalism is suggested to replace the banal, as the former can blend both banal and exceptional reproduction of nationalism in more complex and contingent ways not controlled exclusively by authorities.
IN NN JJ NN VBZ VVN TO VV DT JJ IN DT JJ MD VV DT JJ CC JJ NN IN NN IN JJR JJ CC JJ NNS RB VVN RB IN NNS SENT
(Bi Chongwu, Ye Guanghui, Xia Lixin. Rethinking Knowledge Measurement in Library and Information Science from the Perspective of Citation Content Analysis[J]. Library and Information Service, 2021, 65(21): 97-107.)
doi: 10.13266/j.issn.0252-3116.2021.21.017
(Zhu Qingsong, Leng Fuhai. Topic Identification of Highly Cited Papers Based on Citation Content Analysis[J]. Journal of Library Science in China, 2014, 40(1): 39-49.)
(Yang Siluo, Wang Hao, Wen Tingxiao. Book Influence Studies Based on Citation Analysis with Library and Information Science as Example[J]. Information and Documentation Services, 2010(1): 89-92.)
(Hu Zhigang, Chen Chaomei, Liu Zeyuan, et al. From Counting References to Counting Citations: A New Way to Calculate the Total Cited Times of References[J]. Library and Information Service, 2013, 57(21): 5-10.)
doi: 10.7536/j.issn.0252-3116.2013.21.001
(Lu Chao, Zhang Chengzhi. Study on the Reference Network of Single Academic Article Based on Citation Content[J]. New Technology of Library and Information Service, 2014(10): 33-41.)
(Zhang Chengzhi, Wang Yuzhuo, Lu Chao. Citing Behavior of Academic Monographs——Perspective Based on Character Analysis of Citation Content[J]. Journal of the China Society for Scientific and Technical Information, 2017, 36(3): 319-330.)
(Zhang Chengzhi, Li Zhuo, Zhao Mengyuan, et al. Citing Behavior of Chinese Books Based on Citation Content[J]. Journal of Library Science in China, 2019, 45(3): 96-109.)
(Wang Wenjuan, Ma Jianxia, Chen Chun, et al. A Review of Citation Context Classifications and Implementation Methods[J]. Library and Information Service, 2016, 60(6): 118-127.)
doi: 10.13266/j.issn.0252-3116.2016.06.018
[12]
祝清松, 冷伏海. 引文类型识别研究进展[J]. 图书情报知识, 2013(6): 70-76.
[12]
(Zhu Qingsong, Leng Fuhai. Review of Citation Type Recognition[J]. Documentation, Information & Knowledge, 2013(6): 70-76.)
(Xu Liping, Zeng Yuxian. A Tentative Analysis of the the South China Sea Disputes and Some Trains of Thoughts on the Solutions——Viewed from the Foreign Perspectives[J]. Pacific Journal, 2012, 20(2): 92-98.)
(Xue Li. The South China Sea Issue in the Eyes of American Scholars[J]. Journal of International Relations, 2014(2): 99-108, 156.)
[17]
孙占坤. 日本学者看南海问题[J]. 亚太安全与海洋研究, 2015(6): 6-16, 122.
[17]
(Sun Zhankun. The South China Sea and International Law——The Perspective of Japanese Scholars[J]. Asia-Pacific Security and Maritime Affairs, 2015(6): 6-16, 122.)
(Hua Weina. Research Perspective on South China Sea in Humanities and Social Sciences from the Aspects of World Core Journal Articles[J]. Academics, 2014(10): 206-216, 312.)
(Su Panpan, Du Debin, Liu Chengliang. Global Characteristics of South China Sea and Enlightenments to “Community of Shared Future in the South China Sea”: Taking Published Papers as an Example[J]. Areal Research and Development, 2021, 40(6): 38-42, 50.)
(Sun Haoyang, Shen Guchao. Research on the Extraction Rules of Knowledge Element Contents in the South China Sea Documents of the Republic of China Period[J]. Journal of Intelligence, 2022, 41(12): 132-139.)
(Peng Yufang, Chen Jianghao. Combine Deep Learning with the Rules of Requirement to Construct the “Target Data” Extraction Model for the Academic Literature——Taking the Resources of the South China Sea as an Example[J]. Information Science, 2022, 40(1): 141-147, 157.)
[22]
Chang Y W. A Comparison of Citation Contexts Between Natural Sciences and Social Sciences and Humanities[J]. Scientometrics, 2013, 96(2): 535-553.
doi: 10.1007/s11192-013-0956-1
(Ou Shiyan, Ling Hongfei. A Study of Automatic Classification of Citation Texts and Its Application[J]. Library and Information Service, 2022, 66(16): 125-136.)
doi: 10.13266/j.issn.0252-3116.2022.16.012
(Xu Linhong, Ding Kun, Sun Xiaoling, et al. Research on the Influencing Factors and the Influence of Positive Citation Papers from the Perspective of Citing Papers: Using Natural Language Processing as an Example[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(4): 354-363.)
[25]
McCain K W, Salvucci L J. How Influential is Brooks’ Law? A Longitudinal Citation Context Analysis of Frederick Brooks’ the Mythical Man-Month[J]. Journal of Information Science, 2006, 32(3): 277-295.
doi: 10.1177/0165551506064397
[26]
Yan E J, Chen Z, Li K. Authors’ Status and the Perceived Quality of Their Work: Measuring Citation Sentiment Change in Nobel Articles[J]. Journal of the Association for Information Science and Technology, 2020, 71(3): 314-324.
doi: 10.1002/asi.24237
[27]
Kumar S. Structure and Dynamics of Signed Citation Networks[C]// Proceedings of the 25th International Conference Companion on World Wide Web. 2016: 63-64.
[28]
张家琪. 基于引用内容分析的学术论文价值评价研究[D]. 哈尔滨: 东北林业大学, 2021.
[28]
(Zhang Jiaqi. Research on the Value Evaluation of Academic Papers Based on Citation Context Analysis[D]. Harbin: Northeast Forestry University, 2021.)
(Zhou Wenyuan, Wang Mingyang, Jing Yu. Automatic Classification of Citation Sentiment and Purposes with AttentionSBGMC Model[J]. Data Analysis and Knowledge Discovery, 2021, 5(12): 48-59.)
[30]
Munkhdalai T, Lalor J, Yu H. Citation Analysis with Neural Attention Models[C]// Proceedings of the 7th International Workshop on Health Text Mining and Information Analysis. 2016: 69-77.
[31]
Ravi K, Setlur S, Ravi V, et al. Article Citation Sentiment Analysis Using Deep Learning[C]// Proceedings of the IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing. 2018: 78-85.
[32]
Yousif A, Niu Z D, Chambua J, et al. Multi-Task Learning Model Based on Recurrent Convolutional Neural Networks for Citation Sentiment and Purpose Classification[J]. Neurocomputing, 2019, 335: 195-205.
doi: 10.1016/j.neucom.2019.01.021
(Liu Shengbo, Wang Bo, Tang Delong, et al. Research on Paper Influence Based on Citation Context: A Case Study of the Nobel Prize Winner’s Paper[J]. Library and Information Service, 2015, 59(24): 109-114.)
doi: 10.13266/j.issn.0252-3116.2015.24.016
(Geng Shuqing, Yang Jianlin. A Method to Evaluate the Academic Influence of Papers Based on Citation Sentiment[J]. Information Studies: Theory & Application, 2018, 41(12): 93-98.)
(Li Zheng, Deng Sanhong, Kong Jia, et al. Research on Scholar’s Academic Influence——From the Perspective of Full Citation Data[J]. Library and Information Service, 2020, 64(12): 87-94.)
doi: 10.13266/j.issn.0252-3116.2020.12.010
(Liu Shengbo, Ding Kun, Zhang Chunbo. Research on the Citation Evaluation Based on Citation Context Nature[J]. Information Studies: Theory &Application, 2015, 38(3): 77-81.)
(Collaborative Innovation Center of South China Sea Studies. Bibliographic Index Database for South China Sea[DB/OL]. [2022-03-20]. https://nanhai.nju.edu.cn/5809/list.html. )
[40]
Garfield E. Can Citation Indexing be Automated?[J]. Statistical Association Methods for Mechanized Documentation, 1964, 269: 84-90.
[41]
Shotton D. CiTO, the Citation Typing Ontology[J]. Journal of Biomedical Semantics, 2010, 1(Suppl 1): S6.
doi: 10.1186/2041-1480-1-S1-S6
[42]
Peroni S, Shotton D. FaBiO and CiTO: Ontologies for Describing Bibliographic Resources and Citations[J]. Journal of Web Semantics, 2012, 17:33-43.
doi: 10.1016/j.websem.2012.08.001
[43]
Ciancarini P, di Iorio A, Nuzzolese A G, et al. Evaluating Citation Functions in Cito: Cognitive Issues[C]// Proceedings of the 11th European Semantic Web Conference. 2014: 580-594.
[44]
Teufel S, Siddharthan A, Tidhar D. Automatic Classification of Citation Function[C]// Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing. 2006: 103-110.
(Lu Wei, Meng Rui, Liu Xingbang. A Deep Scientific Literature Mining-oriented Framework for Citation Content Annotation[J]. Journal of Library Science in China, 2014, 40(6): 93-104.)
[46]
Abu-Jbara A, Ezra J, Radev D. Purpose and Polarity of Citation: Towards NLP-Based Bibliometrics[C]// Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. 2013: 596-606.
[47]
Jurgens D, Kumar S, Hoover R, et al. Measuring the Evolution of a Scientific Field Through Citation Frames[J]. Transactions of the Association for Computational Linguistics, 2018, 6: 391-406.
doi: 10.1162/tacl_a_00028
[48]
Taşkın Z, Al U. A Content-Based Citation Analysis Study Based on Text Categorization[J]. Scientometrics, 2018, 114(1): 335-357.
doi: 10.1007/s11192-017-2560-2
(Qiu Junping, Chen Xiaoyu, He Wenjing. Study on Paper Citation Motivations and Mutual Influence of Researchers[J]. Library and Information Service, 2015, 59(9): 36-44.)
doi: 10.13266/j.issn.0252-3116.2015.09.005
(Luo Zhunchen, Zhao He, Ye Yuming, et al. Risk Assessment of Scientific Resources Based on Hyperlink Information Analysis in Literature[J]. Journal of Chinese Information Processing, 2020, 34(5): 64-73.)
[51]
Dong C, Schäfer U. Ensemble-Style Self-Training on Citation Classification[C]// Proceedings of the 5th International Joint Conference on Natural Language Processing. 2015: 623-631.
[52]
Hernández-Alvarez M, Gómez J M. Citation Impact Categorization: For Scientific Literature[C]// Proceedings of the 18th International Conference on Computational Science and Engineering. 2015: 307-313.
(Chen Guo, Xu Tianxiang. Research on Sentence Function Recognition of Scientific Papers Based on Active Learning[J]. Data Analysis and Knowledge Discovery, 2019, 3(8): 53-61.)
[54]
周清清. 基于多源异构数据的图书影响力评价研究[D]. 南京: 南京理工大学, 2018.
[54]
(Zhou Qingqing. Book Impact Assessment Based on Multi-source Heterogeneous Data[D]. Nanjing: Nanjing University of Science and Technology, 2018.)
[55]
曾绍华. 支持向量回归机算法理论研究与应用[D]. 重庆: 重庆大学, 2006.
[55]
(Zeng Shaohua. The Theory Research of Algorithm on Support Vector Regression and Application[D]. Chongqing: Chongqing University, 2006.)
[56]
Stone M. Cross-Validatory Choice and Assessment of Statistical Predictions[J]. Journal of the Royal Statistical Society. Series B (Methodological), 1974, 36(2): 111-147.
doi: 10.1111/j.2517-6161.1974.tb00994.x
(Hong Liang, Ma Feicheng. Knowledge Association Analysis and Big Knowledge Graph Construction for Big Data Management and Decision-Making[J]. Journal of Management World, 2022, 38(1): 207-218.)
(Yang Siluo. Evaluation of International Influence of Humanities and Social Sciences Achievements in China in the New Period: Problems and Trends[J]. Information and Documentation Services, 2020, 41(3): 20-25.)
(National Institute for South China Sea Studies. Wu Shicun: History is the Foundation of the South China Sea’s International Discourse Power[EB/OL]. [2022-08-26]. http://www.Nanhai.org.cn/search-detail/12190/1.html. )