10.7910/DVN/EL3KYD Kaneko, Tomoki Tomoki Kaneko The University of Tokyo Asano, Taka-aki Taka-aki Asano The University of Tokyo Miwa, Hirofumi Hirofumi Miwa Gakushuin University Harvard Dataverse 2020 Social Sciences media slant ideal point estimation quantitative text analysis unsupervised learning Japan Miwa, Hirofumi Hirofumi Miwa Gakushuin University 2020-05-05 2020-06-23 10.7910/DVN/EL3KYD/Q6NEQW 10.7910/DVN/EL3KYD/1EOK3O 10.7910/DVN/EL3KYD/JOYHCL 10.7910/DVN/EL3KYD/O3NSPE 10.7910/DVN/EL3KYD/EOFK3M 10.7910/DVN/EL3KYD/QGQRQQ 10.7910/DVN/EL3KYD/HCVSZC 10.7910/DVN/EL3KYD/HXSKVO 10.7910/DVN/EL3KYD/4VR1MO 10.7910/DVN/EL3KYD/XOXSLH 10.7910/DVN/EL3KYD/GJTIKN 10.7910/DVN/EL3KYD/MGO1AT 10.7910/DVN/EL3KYD/IVB5X9 10.7910/DVN/EL3KYD/TFDJYV 10.7910/DVN/EL3KYD/AYRC0O 10.7910/DVN/EL3KYD/KW13P0 10.7910/DVN/EL3KYD/7YYHFD 10.7910/DVN/EL3KYD/DVA83P 10.7910/DVN/EL3KYD/BFVOIS 10.7910/DVN/EL3KYD/OZNSIM 10.7910/DVN/EL3KYD/ICP7LM 10.7910/DVN/EL3KYD/8AQKHM 10.7910/DVN/EL3KYD/FBQLGL 10.7910/DVN/EL3KYD/86ALJL 10.7910/DVN/EL3KYD/C0KGHK 10.7910/DVN/EL3KYD/UQBHQC 10.7910/DVN/EL3KYD/C6JQLN 10.7910/DVN/EL3KYD/53Y8HT 10.7910/DVN/EL3KYD/DDCIXH 10.7910/DVN/EL3KYD/MWX7IY 10.7910/DVN/EL3KYD/9VZYD9 10.7910/DVN/EL3KYD/VZPDGR 10.7910/DVN/EL3KYD/HTYWSJ 10309026 67667083 5558 6312 7124 11696895 7960 5251 3841402 434 8976 7867 321 13564 2684 3034624 9693 27641 67796623 4046 520 3268 2165 1026524 21168 166921 222777 2006670 2330 8902267 8540 4935 169301 application/gzip application/gzip type/x-r-syntax type/x-r-syntax type/x-r-syntax application/gzip text/tab-separated-values type/x-r-syntax application/gzip type/x-r-syntax type/x-r-syntax type/x-r-syntax type/x-r-syntax type/x-r-syntax type/x-r-syntax application/gzip type/x-r-syntax text/tab-separated-values application/x-rlang-transport type/x-r-syntax text/tab-separated-values type/x-r-syntax type/x-r-syntax application/x-rlang-transport text/tab-separated-values application/gzip application/gzip application/gzip type/x-r-syntax application/x-rlang-transport type/x-r-syntax text/plain text/tab-separated-values 1.0 Creative Commons CC0 1.0 Universal Public Domain Dedication. Although measuring the ideal points of news media is essential for testing political communication theories based on spatial theory, prior methods of estimating ideal points of media outlets have various shortcomings, including high cost in terms of time and human resources and low applicability to different countries. We propose that unsupervised machine learning techniques for text data, specifically the combination of a text scaling method and latent topic modeling, can be applied to estimate ideal points of media outlets. We applied our proposed methods to editorial texts of ten national and regional newspapers in Japan, where prior approaches are not applicable because newspapers have never officially endorsed particular parties or candidates, and because high-quality training data for supervised learning is not available. Our two studies, one of which analyzed editorials on a single typically ideological topic while the other investigated all editorials published by the target papers in one year, confirmed the popular view of Japanese newspapers’ ideological slant, which validates the effectiveness of our proposed approach. We also illustrate that our methods allow scholars to investigate which issues are closely related to the respective ideological positions of media outlets. Furthermore, we use the estimated ideal points of newspapers to show that Japanese people partially tend to read ideologically like-minded newspapers and follow such newspapers’ Twitter accounts even though their slant is not explicit.