Understanding Discourse on Work and Job-Related Well-Being in Public Social Media

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1044–1053, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Understanding Discourse on Work and Job-Related Well-Being in Public Social Media Tong Liu1∗, Christopher M. Homan1∗, Cecilia Ovesdotter Alm1$, Ann Marie White2, Megan C. Lytle2, Henry A. Kautz3 1∗ Golisano College of Computing and Information Sciences, Rochester Institute of Technology 1$ College of Liberal Arts, Rochester Institute of Technology 2 University of Rochester Medical Center 3 Department of Computer Science, University of Rochester tl8313@rit.edu, cmh@cs.rit.edu, coagla@rit.edu annmarie white|megan lytle@urmc.rochester.edu kautz@cs.rochester.edu Abstract We construct a humans-in-the-loop super- vised learning framework that integrates crowdsourcing feedback and local knowl- edge to detect job-related tweets from in- dividual and business accounts. Using data-driven ethnography, we examine dis- course about work by fusing language- based analysis with temporal, geospa- tional, and labor statistics information. 1 Introduction Work plays a major role in nearly every facet of our lives. Negative and positive experiences at work places can have significant social and per- sonal impacts. Employment condition is an im- portant social determinant of health. But how exactly do jobs influence our lives, particularly with respect to well-being? Many theories address this question (Archambault and Grudin, 2012; Schaufeli and Bakker, 2004), but they are hard to validate as well-being is influenced by many fac- tors, including geography as well as social and in- stitutional support. Can computers help us understand the complex relationship between work and well-being? Both are broad concepts that are difficult to capture ob- jectively (for instance, the unemployment rate as a statistic is continually redefined) and thus chal- lenging subjects for computational research. Our first contribution is to propose a classifica- tion framework for such broad concepts as work that alternates between humans-in-the-loop anno- tation and machine learning over multiple itera- tions to simultaneously clarify human understand- ing of these concepts and automatically determine whether or not posts from public social media sites are about work. Our framework balances the ef- fectiveness of crowdsourced workers with local experience, evaluates the degree of subjectivity throughout the process, and uses an iterative post- hoc evaluation method to address the problem of discovering gold standard data. Our performance (on an open-domain problem) demonstrates the value of our humans-in-the-loop approach which may be of special relevance to those interested in discourse understanding, particularly settings characterized by high levels of subjectivity, where integrating human intelligence into active learning processes is essential. Our second contribution is to use our classi- fiers to study job-related discourse on social me- dia using data-driven ethnography. Language is fundamentally a social phenomenon, and social media gives us a lens through which to observe a very particular form of discourse in real time. We add depth to the NLP analysis by gathering data from specific geographical regions to study dis- course along a broad spectrum of interacting so- cial groups, using work as a framing device, and we fuse language-based analysis with temporal, geospatial and labor statistics dimensions. 2 Background …

Content truncated to 500 words