Human Needs Categorization of Affective Events Using Labeled and Unlabeled Data

Proceedings of NAACL-HLT 2018, pages 1919–1929 New Orleans, Louisiana, June 1 - 6, 2018. c⃝2018 Association for Computational Linguistics Human Needs Categorization of Affective Events Using Labeled and Unlabeled Data Haibo Ding School of Computing University of Utah Salt Lake City, UT 84112 hbding@cs.utah.edu Ellen Riloff School of Computing University of Utah Salt Lake City, UT 84112 riloff@cs.utah.edu Abstract We often talk about events that impact us posi- tively or negatively. For example “I got a job” is good news, but “I lost my job” is bad news. When we discuss an event, we not only under- stand its affective polarity but also the reason why the event is beneficial or detrimental. For example, getting or losing a job has affective polarity primarily because it impacts us finan- cially. Our work aims to categorize affective events based upon human need categories that often explain people’s motivations and desires: PHYSIOLOGICAL, HEALTH, LEISURE, SO- CIAL, FINANCIAL, COGNITION, and FREE- DOM. We create classification models based on event expressions as well as models that use contexts surrounding event mentions. We also design a co-training model that learns from unlabeled data by simultaneously train- ing event expression and event context classi- fiers in an iterative learning process. Our re- sults show that co-training performs well, pro- ducing substantially better results than the in- dividual classifiers. 1 Introduction Recent research has focused on identifying affec- tive events in text, which are activities or states that positively or negatively affect the people who experience them. Recognizing affective events in text is challenging because they appear as factual expressions and their affective polarity is often im- plicit. For example, “I broke my arm” and “I got fired” are usually negative experiences, while “I broke a record” and “I went to a concert” are typically positive experiences. Several NLP tech- niques have been developed to recognize affec- tive events, including patient polarity verb boot- strapping (Goyal et al., 2010, 2013), implicature rules (Deng and Wiebe, 2014), label propagation (Ding and Riloff, 2016), pattern-based learning (Vu et al., 2014; Reed et al., 2017), and semantic consistency optimization (Ding and Riloff, 2018). Our research aims to probe deeper and under- stand not just the polarity of affective events, but the reason for the polarity. Events can impact peo- ple in many ways, and understanding why an event is beneficial or detrimental is a fundamental as- pect of language understanding and narrative text comprehension. Additionally, many applications could benefit from understanding the nature of af- fective events, including text summarization, con- versational dialogue processing, and mental health therapy or counseling systems. As an illustra- tion, a mental health therapy system can benefit from understanding why someone is in a negative state. If the triggering event for depression is “I broke my leg” then the reason is about the per- son’s Health, but if the triggering event is “I broke up with my girlfriend” then the reason is based on Social relationships. We hypothesize that the polarity of affective events can often …

Content truncated to 500 words