TY - JOUR
T1 - Understanding the social construction of juvenile delinquency
T2 - insights from semantic analysis of big-data historical newspaper collections
AU - Zhang, Yu
AU - Davies, Adam
AU - Zhai, Cheng Xiang
N1 - This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation grant number ACI-1548562. Specifically, it used the Bridges system, which is supported by NSF award number ACI-1445606, at the Pittsburgh Supercomputing Center (PSC) through allocation TG-SES170016. We thank the XSEDE Extended Collaborative Support Service (ECSS) program. This work also made use of the Illinois Campus Cluster, a computing resource that is operated by the Illinois Campus Cluster Program (ICCP) in conjunction with the National Center for Supercomputing Applications (NCSA) and which is supported by funds from the University of Illinois at Urbana-Champaign. This work also utilized resources supported by the National Science Foundation\u2019s Major Research Instrumentation Program, grant number 1725729, as well as the University of Illinois at Urbana-Champaign. We thank the Cline Center for Advanced Social Research and the University of Illinois at Urbana-Champaign for providing access to ProQuest Historical NewspapersTM. Finally, we express our appreciation to Alan Craig, Sandeep Puthanveetil Satheesan, and Bhavya for both their feedback on this draft and their contributions to the text analysis system used in this work (as described in our earlier publication, Satheesan et al. [36]).
This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation grant number ACI-1548562. Specifically, it used the Bridges system, which is supported by NSF award number ACI-1445606, at the Pittsburgh Supercomputing Center (PSC) through allocation TG-SES170016. We thank the XSEDE Extended Collaborative Support Service (ECSS) program. This work also made use of the Illinois Campus Cluster, a computing resource that is operated by the Illinois Campus Cluster Program (ICCP) in conjunction with the National Center for Supercomputing Applications (NCSA) and which is supported by funds from the University of Illinois at Urbana-Champaign. This work also utilized resources supported by the National Science Foundation\u2019s Major Research Instrumentation Program, grant number 1725729, as well as the University of Illinois at Urbana-Champaign. We thank the Cline Center for Advanced Social Research and the University of Illinois at Urbana-Champaign for providing access to ProQuest Historical Newspapers. Finally, we express our appreciation to Alan Craig, Sandeep Puthanveetil Satheesan, and Bhavya for both their feedback on this draft and their contributions to the text analysis system used in this work (as described in our earlier publication, Satheesan et al. []).
PY - 2024/10
Y1 - 2024/10
N2 - Massive historical newspaper collections contain rich information about the historical development of social issues and constitute a unique resource for studying the social construction of issues such as juvenile delinquency. However, manual analysis of millions of pages of newspaper articles is infeasible. In this paper, we propose a suite of computational methods, including cross-context lexical analysis, dynamic semantic analysis, and valence analysis, to facilitate the study of historical social construction. We apply these methods to ProQuest Historical NewspapersTM collection in the period of 1790–2006 to study the social construction of juvenile delinquency over this period. Our results show that the proposed methods are effective in revealing insights regarding the social construction of juvenile delinquency, leading to a better understanding of this complex issue and specific hypotheses for further study. Overall, our study shows the great promise of leveraging natural language processing techniques for analyzing historical news data to study social construction of societal issues.
AB - Massive historical newspaper collections contain rich information about the historical development of social issues and constitute a unique resource for studying the social construction of issues such as juvenile delinquency. However, manual analysis of millions of pages of newspaper articles is infeasible. In this paper, we propose a suite of computational methods, including cross-context lexical analysis, dynamic semantic analysis, and valence analysis, to facilitate the study of historical social construction. We apply these methods to ProQuest Historical NewspapersTM collection in the period of 1790–2006 to study the social construction of juvenile delinquency over this period. Our results show that the proposed methods are effective in revealing insights regarding the social construction of juvenile delinquency, leading to a better understanding of this complex issue and specific hypotheses for further study. Overall, our study shows the great promise of leveraging natural language processing techniques for analyzing historical news data to study social construction of societal issues.
KW - Computational semantics
KW - Historical newspapers
KW - Juvenile delinquency
KW - Natural language processing
KW - Social construction
KW - Word embeddings
UR - https://www.scopus.com/pages/publications/85192826831
UR - https://www.scopus.com/pages/publications/85192826831#tab=citedBy
U2 - 10.1007/s42001-024-00254-x
DO - 10.1007/s42001-024-00254-x
M3 - Article
AN - SCOPUS:85192826831
SN - 2432-2717
VL - 7
SP - 1095
EP - 1137
JO - Journal of Computational Social Science
JF - Journal of Computational Social Science
IS - 2
ER -