AI for Social Justice: New Methodological Horizons in Technical Communication

ABSTRACT This Methodologies and Approaches piece argues artificially intelligent machine learning systems can be used to effectively advance justice-oriented research in technical and professional communication (TPC). Using a preexisting dataset investigating patient marginalization in pharmaceuticals policy discourse, we built and tested 49 machine learning systems designed to identify and track rhetorical features of interest. Three popular and one new approach to feature engineering (text quantification) were evaluated. The results indicate that these systems have great potential for use in TPC research.

[1]  Natalia Kovalyova,et al.  Data feminism , 2020, Information, Communication & Society.

[2]  Shigeo Abe.  Support Vector Machines for Pattern Classification , 2010, Advances in Pattern Recognition.

[3]  D. Haraway,et al.  Modest_Witness@Second_Millennium. FemaleMan_Meets_OncoMouse , 1997 .

[4]  A. B. M. Shawkat Ali,et al.  Support Vector Machine: Itself an Intelligent Systems , 2009 .

[5]  N. Jones.  The Technical Communicator as Advocate , 2016 .

[6]  L. Foster-Johnson,et al.  Peer Review in Biology: Of Novices, Experts, and Disciplines , 2019, The Journal of Writing Analytics.

[7]  Caitlin E. Starks.  Technical Communication After the Social Justice Turn: Building Coalitions for Action: Rebecca Walton, Kristen R. Moore, and Natasha N. Jones [Book Review] , 2020, IEEE Transactions on Professional Communication.

[8]  Avery C. Edenfield,et al.  Queering Tactical Technical Communication: DIY HRT , 2019, Technical Communication Quarterly.

[9]  Ashley Rose Mehlenbacher.  Rhetorical figures as argument schemes - The proleptic suite , 2017, Argument Comput..

[10]  Emma Rodman,et al.  A Timely Intervention: Tracking the Changing Meanings of Political Concepts with Word Vectors , 2019, Political Analysis.

[11]  S. Noble.  Algorithms of Oppression: How Search Engines Reinforce Racism , 2018 .

[12]  Chris Dayley.  Student Perceptions of Diversity in Technical and Professional Communication Academic Programs , 2019, Technical Communication Quarterly.

[13]  Sang-Yeon Kim,et al.  Statistical Genre Analysis: Toward Big Data Methodologies in Technical Communication , 2015 .

[14]  Franco Turini,et al.  A Survey of Methods for Explaining Black Box Models , 2018, ACM Comput. Surv..

[16]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[17]  S. Graham.  The Opioid Epidemic and the Pursuit of Moral Medicine: A Computational-Rhetorical Analysis , 2020 .

[18]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Neural Networks , 2013 .

[19]  Rebecca Walton,et al.  Technical Communication after the Social Justice Turn , 2019 .

[20]  Tomas Mikolov,et al.  Bag of Tricks for Efficient Text Classification , 2016, EACL.

[21]  S. Merz.  Race after technology. Abolitionist tools for the new Jim Code , 2020, Ethnic and Racial Studies.

[22]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[23]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[24]  James E. Dobson,et al.  Can An Algorithm Be Disturbed?: Machine Learning, Intrinsic Criticism, and the Digital Humanities , 2015 .

[25]  William Hart-Davidson,et al.  Finding genre signals in academic writing , 2016 .

[26]  Rebecca Walton,et al.  Disrupting the Past to Disrupt the Future: An Antenarrative of Technical Communication , 2016 .

[27]  B. Efron.  Better Bootstrap Confidence Intervals , 1987 .

[28]  Prabhat,et al.  Artificial Neural Network , 2018, Encyclopedia of GIS.

[29]  L. F. Molerio-Leon,et al.  Survey Methods , 2011 .

[30]  William Hart-Davidson,et al.  Genre Signals in Textual Topologies , 2017 .

[32]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[33]  Tunga Güngör,et al.  Part-of-Speech Tagging , 2005 .