CancerEmo: A Dataset for Fine-Grained Emotion Detection

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8892–8904, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 8892 CANCEREMO : A Dataset for Fine-Grained Emotion Detection Tiberiu Sosea and Cornelia Caragea Computer Science Department University of Illinois at Chicago tsosea2@uic.edu, cornelia@uic.edu, Abstract Emotions are an important element of human nature, often affecting the overall wellbeing of a person. Therefore, it is no surprise that the health domain is a valuable area of interest for emotion detection, as it can provide medical staff or caregivers with essential information about patients. However, progress on this task has been hampered by the absence of large labeled datasets. To this end, we introduce CANCEREMO , an emotion dataset created from an online health community and anno- tated with eight fine-grained emotions. We per- form a comprehensive analysis of these emo- tions and develop deep learning models on the newly created dataset. Our best BERT model achieves an average F1 of 71%, which we improve further using domain-specific pre- training. 1 Introduction Life-threatening diseases such as cancer and AIDS make people extremely vulnerable and stir a di- verse range of feelings and emotions in them, e.g., from fear to trust or joy and from anger to surprise or sadness. These feelings and emotions shape a person’s behavior, beliefs, and actions, and many turn to online health communities to share their health concerns and emotions. Recent research shows that this form of sharing is very beneficial to a patient’s progress and well-being. For exam- ple, Qiu et al. (2011) show that cancer patients feel better and change to positive attitudes when they in- teract with others during or after the disease. Pollak et al. (2007) show that less anxiety and depression lead to better adherence to cancer care therapies. The online sharing of emotions in online health communities on topics such as treatment, medica- tion, side effects, moods, and the disease itself, has resulted into a large amount of user-generated con- tent in the form of discussions. This together with the fact that people find it easier to express them- selves and reveal personal details in health forums, rather than in a face-to-face context (Kummervold et al., 2002), make online health communities a great place to examine and study patients’ emo- tions at a large scale using computational models. However, despite that emotion detection has started to emerge in the health domain, the lack of large annotated datasets in the field greatly hin- ders the capabilities of supervised techniques and limits an understanding of fine-grained expressions of emotions at a large scale. For example, avail- able datasets contain only about 1, 000 sentences annotated with Ekman’s six basic emotions. Since some emotions appear very rarely in the annotated set, only the most frequent ones joy and sadness are analyzed (Khanpour and Caragea, 2018). In this paper, we explore fine-grained emotion detection in online health communities and present a large dataset for this task. Specifically, we in- troduce CANCEREMO , a health-related …

Content truncated to 500 words