LSS: Semi-supervised algorithm for document scaling

In quantitative text analysis, the cost of training supervised machine learning models tend to be very high when the corpus is large. Latent Semantic Scaling (LSS) is a semi-supervised document scaling technique that I developed to perform large scale analysis at low cost. Taking user-provided seed words as weak supervision, it estimates polarity of words in the corpus by latent semantic analysis and locates documents on a unidimensional scale (e.g. sentiment).

Installation

From CRAN:

install.packages("LSX")

From Github:

devtools::install_github("koheiw/LSX")

Examples

Please visit the package website to understand the usage of the functions:

• Introduction to LSX
• Application in research
• Selection of seed words

Please read the following papers for the algorithm and methodology, and its application to non-English texts (Japanese and Hebrew):

• Watanabe, Kohei. 2020. “Latent Semantic Scaling: A Semisupervised Text Analysis Technique for New Domains and Languages”, Communication Methods and Measures.
• Watanabe, Kohei, Segev, Elad, & Tago, Atsushi. (2022). “Discursive diversion: Manipulation of nuclear threats by the conservative leaders in Japan and Israel”, International Communication Gazette.

Other publications

LSS has been used for research in various fields of social science.

• Nakamura, Kentaro. 2022 Balancing Opportunities and Incentives: How Rising China’s Mediated Public Diplomacy Changes Under Crisis, International Journal of Communication.
• Zollinger, Delia. 2022 Cleavage Identities in Voters’ Own Words: Harnessing Open-Ended Survey Responses, American Journal of Political Science.
• Brändle, Verena K., and Olga Eisele. 2022. “A Thin Line: Governmental Border Communication in Times of European Crises” Journal of Common Market Studies.
• Umansky, Natalia. 2022. “Who gets a say in this? Speaking security on social media”. New Media & Society.
• Rauh, Christian, 2022. “Supranational emergency politics? What executives’ public crisis communication may tell us”, Journal of European Public Policy.
• Trubowitz, Peter and Watanabe, Kohei. 2021. “The Geopolitical Threat Index: A Text-Based Computational Approach to Identifying Foreign Threats”, International Studies Quarterly.
• Vydra, Simon and Kantorowicz, Jaroslaw. 2020. “Tracing Policy-relevant Information in Social Media: The Case of Twitter before and during the COVID-19 Crisis”. Statistics, Politics and Policy.
• Watanabe, Kohei. 2017. “Measuring News Bias: Russia’s Official News Agency ITAR-TASS’s Coverage of the Ukraine Crisis”, European Journal Communication.

More publications are available on Google Scholar.