Discovering Interdisciplinary Research Based on Word Embedding

doi:10.11871/jfdc.issn.2096-742X.2021.06.004

Abstract

Abstract:

[Objective] Interdisciplinary research has promoted the emergence of many major scientific discoveries, hence researchers need to identify interdisciplinary problems in their research field. Since huge number of scientific papers have been published today, it is difficult to discover interdisciplinary research manually, automatic searching methods are needed.[Methods] This paper proposes an approach to discover interdisciplinary research automatically. This method adopts the word embedding mechanism in artificial intelligence, which covers approximately 1.7 million vocabularies of natural sciences. It captures interdisciplinary research by automatically identifying the keywords with semantic anomalies from the author's keywords. [Results] The method is applied to the research field of deep learning and discovers some interdisciplinary natural science research. [L-imitations] Due to the shortcomings of traditional word embedding in representing the word with multiple meanings, the recognition accuracy of keywords with semantic anomalies needs to be improved. [Conclusions] The proposed method is a novel solution to the discovery of interdisciplinary research.

Key words: interdisciplinary research, word embedding, semantic anomaly, deep learning

HE Tao,WANG Guifang,MA Tingcan. Discovering Interdisciplinary Research Based on Word Embedding[J]. Frontiers of Data and Computing, 2021, 3(6): 50-59.

Figures/Tables 5

Fig.1

Fig.2

Table 1

Fig.3

Table 2

References 25

[1]	张雪, 张志强. 学科交叉研究系统综述[J]. 图书情报工作, 2020,64(14):112-125.
[2]	刘群, 李素建. 基于《知网》的词汇语义相似度计算[J]. 中文计算语言学, 2002,7(2):59-76.
[3]	Dong K, Xu H, Luo R, et al. An integrated method for interdisciplinary topic identification and prediction: a case study on information science and library science[J]. Scientometrics, 2018,115(2):849-868.
[4]	商宪丽. 基于潜在主题的交叉学科知识组合与知识传播研究[D]. 华中师范大学, 2017.
[5]	吴蕾, 田儒雅, 张学福. 基于主题相关分析的跨学科主题发现方法及实证研究—以动物资源与育种领域为例[J]. 图书情报工作, 2017,61(01):72-79.
[6]	Porter A, Cohen A, Roessner D, et al. Measuring resear-cher interdisciplinarity[J]. Scientometrics, 2007,72(1):117-147.
[7]	Mugabushaka A, Kyriakou A, Papazoglou T. Bibliometric indicators of interdisciplinarity: the potential of the lein-ster-cobbold diversity indices to study disciplinary diver-sity[J]. Scientometrics, 2016,107(2):593-607.
[8]	Schummer J. Multidisciplinarity, interdisciplinarity, and patterns of research collaboration in nanoscience and nanotechnology[J]. Scientometrics, 2004,59(3):425-465.
[9]	Abramo G, Angelo A, Costa D. Identifying interdiscip-linarity through the disciplinary classification of coauthors of scientific publications[J]. Journal of the American Society for Information Science and Technology, 2012,63(11):2206-2222.
[10]	杜德慧, 李长玲, 相富钟, 等. 基于引文关键词的跨学科相关知识发现方法探讨[J]. 情报杂志, 2020,39(9):189-194.
[11]	刘小慧, 李长玲, 崔斌, 等. 基于闭合式非相关知识发现的潜在跨学科合作研究主题识别—以情报学与计算机科学为例[J]. 情报理论与实践, 2017,40(09):71-76.
[12]	李长玲, 刘小慧, 刘运梅, 等. 基于开放式非相关知识发现的潜在跨学科合作研究主题识别—以情报学与计算机科学为例[J]. 情报理论与实践, 2018,41(02):100-104.
[13]	魏建香, 孙越泓, 苏新宁. 学科交叉知识挖掘模型研究[J]. 情报理论与实践, 2012,35(04):76-80.
[14]	王卫军, 姚畅, 乔子越, 等. 基于词嵌入的国家自然科学基金学科交叉知识发现方法——以“人工智能”与“信息管理”为例[J]. 情报学报, 2021,40(08):831-845.
[15]	Xu H, Guo T, Yue Z, et al. Interdisciplinary topics of information science: a study based on the terms interdisci-plinarity index series[J]. Scientometrics, 2016,106(2):583-601.
[16]	Mao J, Liang Z, Cao Y, et al. Quantifying cross-dis-ciplinary knowledge flow from the perspective of con-tent: Introducing an approach based on knowledge memes[J]. Journal of Informetrics, 2020 14(4), Art. no. 101092.
[17]	Kamada M, Asatani K, Isonuma M, et al. Discovering interdisciplinarily spread knowledge in the academic literature[J]. IEEE Access, 2021,9(1):124142-124151.
[18]	Mikolov T, Sutskever I, Chen K, et al. Distributed rep-resentations of words and phrases and their composition-ality[C]. Advances in Neural Information Processing Sy-stems. Lake Tahoe, USA: Curran Associates, 2013: 3111-3119.
[19]	Everitt BS, Dunn G. Applied multivariate data analysis, second edition[M]. Oxford: Oxford University Press, 2013: 48-73.
[20]	松尾丰. 人工智能狂潮[M]. 北京: 机械工业出版社, 2016: 110-111.
[21]	何涛, 王桂芳, 杨美妮, 等. 基于词嵌入语义的精准检索式构建方法[J]. 现代情报, 2018,38(11):55-58.
[22]	Li K, Huang H, Tian S, et al. Improving one-class SVM for anomaly detection[C]. The 2003 International Confe-rence on Machine Learning and Cybernetics. Manhattan: IEEE, 2003: 3077-3081.
[23]	Liu F, Ting K, Zhou Z. Isolation forest[C]. Eighth IEEE International Conference on Data Mining. Manhattan: IEEE, 2008: 413-422.
[24]	Breunig MM, Kriegel HP, Ng RT, et al. LOF: identifying density-based local outliers[C]. SIGMOD Conference on Management of Data. Texas: ACM Press, 2000: 93-104.
[25]	Peters ME, Neumann M, Iyyer M, et al. Deep contextua-lized word representations[C]. North American Associa-tion for Computational Linguistics. New Orleans: Asso-ciation for Computer Linguistics, 2018: 2227-2237.

	常见于深度学习的研究论文	含有跨学科研究内容的语义	作者关键词
异常程度最高的10个作者关键词	否	是	A: “rice seed”, “food recognition”, “optical music recognition”, “hot deformation”, “rna-binding protein”, “froth flotation”, “cluster finding”
	否	否	B: “grand challenge”
	是	否	C: “network compression”, “trigger detection”
异常程度最低的10个作者关键词	是	否	“image classification”, “feature representation”, “feature extraction”, “image representation”, “human action recognition”, “deep learning”, “feature fusion”, “computer vision”, “image recognition”, “discriminative features”

	文章标题	异常关键词	跨学科研究内容
1	Variety identification of single rice seed using hyperspectral imaging combined with convolutional neural network.	rice seed	在食品科学中使用深度学习对水稻纯度进行研究。
2	Hot deformation characteristics and dislocation substructure evolution of a nickel-base alloy considering effects of delta phase.	hot deformation	在冶金领域使用深度学习对热变形进行研究。
3	UV-flashover evaluation of porcelain insulators based on deep learning.	ultraviolet spectra	在电力传输中使用深度学习进行器件的绝缘特性研究。
4	In situ monitoring of selective laser melting using plume and spatter signatures by deep belief networks.	selective laser melting	在金属部件制作中使用深度学习对选择性激光断融进行研究。
5	Image-based deep learning for classification of noise tran-sients in gravitational wave detectors.	gravitational waves	在引力波侦测中使用深度学习对噪声进行分类。