{"id":488,"date":"2021-06-15T13:00:37","date_gmt":"2021-06-15T13:00:37","guid":{"rendered":"http:\/\/hnr2021.historicalnetworkresearch.org\/?page_id=488"},"modified":"2021-06-21T12:58:44","modified_gmt":"2021-06-21T12:58:44","slug":"from-textual-to-historical-networks-reconstructing-social-relations-among-chinese-elites-from-the-biographical-dictionary-of-republican-china-brdc","status":"publish","type":"page","link":"http:\/\/hnr2021.historicalnetworkresearch.org\/?page_id=488","title":{"rendered":"From Textual to Historical Networks: Reconstructing Social Relations among Chinese Elites from the Biographical Dictionary of Republican China (BRDC)"},"content":{"rendered":"\n

Christian Henriot <\/em>and Cecile Armand<\/h2>\n\n\n\n

Time and Place:<\/strong> Thursday, 01.07., 14:45\u201315:05, Room 2
Session:<\/strong> Biographies and Careers in China<\/p>\n\n\n\n

Keywords: <\/strong>China; elite; biography; NLP<\/p>\n\n\n\n

Background<\/strong><\/p>\n\n\n\n

Our objective is fourfold: to reconstruct the network of social relations among\u00a0 historical figures extracted from a biographical dictionary, the Biographical Dictionary of\u00a0 Republican China (BRDC); to derive a network of social relations from networks of words; to reveal\u00a0 hidden patterns of connections within and across the articles, and between individuals (as well as\u00a0 institutions and places); to propose ultimately an alternative non-linear reading of this dictionary.\u00a0\u00a0<\/p>\n\n\n\n

Methods and dat<\/strong>a<\/p>\n\n\n\n

The BDRC consists of 4 volumes of about 500 pages each and an index volume.\u00a0 The four main volumes describe 588 individuals. To extract and analyze relations, we proceeded in\u00a0 three steps:<\/p>\n\n\n\n

  1. Building networks of words: We developed a specific workflow to automatically extract\u00a0 relations between entities from the BDRC, relying on Named Entity Recognition (NER) and a\u00a0 visualization tool (Padagraph) (Magistry et al., 2019). We extracted not only individuals but also\u00a0 institutions, places and events. The first challenge was language (Chinese, English, Wade-Giles\u00a0 transliteration) and inconsistencies in naming entities across the book. This involved a long\u00a0 process of human checking\/cleaning data produced a mapping of all entities and their\u00a0 connections. Yet as social historians, we are not just interested in relations between named\u00a0 entities per se, but in retrieving actual relations between historical actors from the extracted\u00a0 words. To exemplify the issue of moving from named entities to actors, we focused on\u00a0 interpersonal relations (relations between individuals).<\/li>
  2. Reconstructing interpersonal networks: We examined the relations between individuals\u00a0 regardless of the nature of the relations, using directed networks, various centrality measures\u00a0 (degree, betweenness) and clustering techniques in Cytoscape: (1) We distinguished between\u00a0 \u201cbiographical nodes\u201d (bionodes) \u2013 i.e. individuals who are the subject of an entry in the BDRC – and\u00a0 non-biographical nodes (individuals only mentioned in an entry); (2) We identified different\u00a0 profiles depending on their position in the network (bionodes, brokers, outsiders); (3) We focused\u00a0 on \u201cbrokers\u201d \u2013 actors who are not necessarily central in the BDRC, but who nevertheless occupied\u00a0 a pivotal position in our network, by linking disconnected data on actors in the articles; (4) We\u00a0 identified different clusters of relations that suggested patterns of political, professional, or\u00a0 kinship affiliations.<\/li>
  3. Classifying relationships: We propose to move beyond the sentiment analysis classification\u00a0 of relations used in previous studies (De Camp, 2011) and common in contemporary SNA (like with\u00a0 Facebook data) in order to build an ontology of historical relations: (1) We first distinguished\u00a0 between actual\/ social and textual\/contextual relationships (simple co-occurrences of words); (2)\u00a0 Then we qualified more specifically the nature of relationships (personal, political, business,\u00a0 kinship, etc.) using a four-step approach: (a) annotating relations in a representative sample of\u00a0 articles using InCeption; (b) applying these annotations to the entire corpus (c) checking-and correcting possible errors and inconsistencies (d) visualizing and analyzing results using Cytoscape.<\/li><\/ol>\n\n\n\n

    Findings<\/strong><\/p>\n\n\n\n

    We observed that \u201cbionodes\u201d were not necessarily the most central actors \u2013 in terms of\u00a0 degree centrality (number\/density of connections) \u2013 although the top ten includes well-known\u00a0 figures of political or military leaders (Chiang Kai-shek, Sun Yat-Sen, Yuan Shikai, Mao Zedong,\u00a0 Zhou Enlai). SNA highlights a mixed group of intermediate characters in politics (Zhang Binglin),\u00a0 academia (Li Dazhao), and the military (Li Zhongren). Intellectuals, including some with religious\u00a0 affiliation, often play the role of brokers in the whole network. Furthermore, community detection\u00a0 brings to the fore groups around individuals that we did not expect, particularly women (such as\u00a0 Song Meiling). Finally, the network of classified relations, combined with clustering techniques,\u00a0 helps redefine new configurations of social and political power among Chinese Republican elites.\u00a0\u00a0<\/p>\n\n\n\n

    References<\/strong>\u00a0\u00a0<\/p>\n\n\n\n

    Boorman, H.L. Biographical Dictionary of Republican China (New York: Columbia University Press,  1967).  <\/p>\n\n\n\n

    Camp, Matje van de, and Antal van den Bosch. \u201cA Link to the Past: Constructing Historical Social  Networks.\u201d In Proceedings of the 2Nd Workshop on Computational Approaches to Subjectivity and  Sentiment Analysis, 61\u201369. WASSA\u201911. Stroudsburg, PA, USA: Association for Computational  Linguistics, 2011.  <\/p>\n\n\n\n

    Magistry, P. et al. Mining the Biographical Dictionary of Republican China. From print to network  exploration. In Proceedings of the 3rd Conference on Biographical Data in a Digital World 2019.  Varna, Bulgaria, 2019.  <\/p>\n\n\n\n

    InCeption. https:\/\/inception-project.github.io\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

    Christian Henriot and Cecile Armand Time and Place: Thursday, 01.07., 14:45\u201315:05, Room 2Session: Biographies and Careers in China Keywords: China; elite; biography; NLP Background Our objective is fourfold: to reconstruct the network of social relations among\u00a0 historical figures extracted from a biographical dictionary, the Biographical Dictionary of\u00a0 Republican China (BRDC); to derive a network of social relations from networks of<\/p>\n

    Weiterlesen<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":98,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"_links":{"self":[{"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=\/wp\/v2\/pages\/488"}],"collection":[{"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=488"}],"version-history":[{"count":4,"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=\/wp\/v2\/pages\/488\/revisions"}],"predecessor-version":[{"id":650,"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=\/wp\/v2\/pages\/488\/revisions\/650"}],"up":[{"embeddable":true,"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=\/wp\/v2\/pages\/98"}],"wp:attachment":[{"href":"http:\/\/hnr2021.historicalnetworkresearch.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=488"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}