ABSTRACT
During the pandemic caused by coronavirus disease (COVID-19), social media has played an important role by enabling people to discuss their experiences and feelings of this global crisis. To help combat the prolonged pandemic that has exposed vulnerabilities impacting community resilience, in this paper, based on our established large-scale COVID-19 related social media data, we propose and develop an integrated framework (named Dr.Emotion) to learn disentangled representations of social media posts (i.e., tweets) for emotion analysis and thus to gain deep insights into public perceptions towards COVID-19. In Dr.Emotion, for given social media posts, we first post-train a transformer-based model to obtain the initial post embeddings. Since users may implicitly express their emotions in social media posts which could be highly entangled with other descriptive information in the post content, to address this challenge for emotion analysis, we propose an adversarial disentangler by integrating emotion-independent (i.e., sentiment-neutral) priors of the posts generated by another post-trained transformer-based model to separate and disentangle the implicitly encoded emotions from the content in latent space for emotion classification at the first attempt. Extensive experimental studies are conducted to fully evaluate Dr.Emotion and promising results demonstrate its performance in emotion analysis by comparison with the state-of-the-art baseline methods. By exploiting our developed Dr.Emotion, we further perform emotion analysis over a large number of social media posts and provide in-depth investigation from both temporal and geographical perspectives, based on which additional work can be conducted to extract and transform the constructive ideas, experiences and support into actionable information to improve community resilience in responses to a variety of crises created by COVID-19 and well beyond.
- Vikash Balasubramanian, Ivan Kobyzev, Hareesh Bahuleyan, Ilya Shapiro, and Olga Vechtomova. 2020. Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation. arXiv preprint arXiv:2004.10809(2020).Google Scholar
- Yu Bao, Hao Zhou, Shujian Huang, Lei Li, Lili Mou, Olga Vechtomova, Xinyu Dai, and Jiajun Chen. 2019. Generating Sentences from Disentangled Syntactic and Semantic Spaces. In ACL. 6008–6019.Google Scholar
- Alexander W. Bartik, Marianne Bertrand, Zoë B. Cullen, Edward L. Glaeser, Michael Luca, and Christopher T. Stanton. 2020. How are small businesses adjusting to covid-19? early evidence from a survey. National Bureau of Economic Research(2020).Google ScholarCross Ref
- BEA. 2020. Gross Domestic Product (Third Estimate), Corporate Profits (Revised), and GDP by Industry, Second Quarter 2020. https://www.bea.gov/news/2020/gross-domestic-product-third-estimate-corporate-profits-revised-and-gdp-industry-annual.Google Scholar
- BLS. 2020. The employment situation - May 2020. https://www.bls.gov/news.release/pdf/empsit.pdf.Google Scholar
- Mingda Chen, Qingming Tang, Sam Wiseman, and Kevin Gimpel. 2019. A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations. In NAACL. 2453–2464.Google Scholar
- Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. 2016. Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In NIPS. 2172–2180.Google Scholar
- E. H. Coe and K. Enomoto. 2020. Returning to resilience: The impact of COVID-19 on mental health and substance use. https://www.mckinsey.com/industries/healthcare-systems-and-services/our-insights/returning-to-resilience-the-impact-of-covid-19-on-behavioral-health.Google Scholar
- Ning Dai, Jianze Liang, Xipeng Qiu, and Xuan-Jing Huang. 2019. Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation. In ACL. 5997–6007.Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).Google Scholar
- Dr.Emotion. 2020. Sample dataset and open-source codes of Dr.Emotion. https://github.com/www2021DrEmotion/www2021DrEmotion.Google Scholar
- Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, and Jianxin Liao. 2020. Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis. In ACL. 4019–4028.Google Scholar
- Akash Dutt Dubey. 2020. Decoding the Twitter Sentiments towards the Leadership in the times of COVID-19: A Case of USA and India. SSRN:3588623 (2020).Google Scholar
- Viet Duong, Phu Pham, Tongyu Yang, Yu Wang, and Jiebo Luo. 2020. The ivory tower lost: How college students respond differently than the general public to the covid-19 pandemic. arXiv preprint arXiv:2004.09968(2020).Google Scholar
- Emilien Dupont. 2018. Learning disentangled joint continuous and discrete representations. In NIPS. 710–720.Google Scholar
- Pablo Gamallo and Marcos Garcia. 2014. Citius: A NaiveBayes Strategy for Sentiment Analysis on English Tweets. In SemEval. Citeseer.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In NIPS. 2672–2680.Google Scholar
- Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework.ICLR 2, 5 (2017), 6.Google Scholar
- Sepp Hochreiter, Yoshua Bengio, Paolo Frasconi, Jürgen Schmidhuber, 2001. Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. A field guide to dynamical recurrent neural networks (2001).Google Scholar
- Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward controlled generation of text. In ICML. 1587–1596.Google Scholar
- JHU. 2020. Coronavirus COVID-19 Global Cases. https://coronavirus.jhu.edu/map.html.Google Scholar
- Vineet John, Lili Mou, Hareesh Bahuleyan, and Olga Vechtomova. 2019. Disentangled Representation Learning for Non-Parallel Text Style Transfer. In ACL. 424–434.Google Scholar
- Heather J. Kagan. 2020. Opioid overdoses on the rise during COVID-19 pandemic, despite telemedicine care. https://abcnews.go.com/Health/opioid-overdoses-rise-covid-19-pandemic-telemedicine-care/story?id=72442735.Google Scholar
- Yoon Kim. 2014. Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882(2014).Google Scholar
- Bennett Kleinberg, Isabelle van der Vegt, and Maximilian Mozes. 2020. Measuring emotions in the covid-19 real world worry dataset. arXiv preprint arXiv:2004.04225(2020).Google Scholar
- Guillaume Lample and Alexis Conneau. 2019. Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291(2019).Google Scholar
- Maria Larsson, Amanda Nilsson, and Mikael Kågebäck. 2017. Disentangled representations for manipulation of sentiment in text. arXiv preprint arXiv:1712.10066(2017).Google Scholar
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692(2019).Google Scholar
- Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Raetsch, Sylvain Gelly, Bernhard Schölkopf, and Olivier Bachem. 2019. Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations. In ICML. 4114–4124.Google Scholar
- Yukun Ma, Haiyun Peng, and Erik Cambria. 2018. Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM.. In AAAI. 5876–5883.Google Scholar
- Andrew Maas, Raymond E Daly, Peter T Pham, Dan Huang, Andrew Y Ng, and Christopher Potts. 2011. Learning word vectors for sentiment analysis. In ACL: HLT. 142–150.Google Scholar
- Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, Nov (2008), 2579–2605.Google Scholar
- Saif M Mohammad and Peter D Turney. 2013. Nrc emotion lexicon. National Research Council, Canada 2 (2013).Google Scholar
- NY-Governor. May 20, 2020. Following Spike in Domestic Violence During COVID-19 Pandemic, Secretary to the Governor Melissa Derosa & NYS Council on Women & Girls Launch Task Force to Find Innovative Solutions to Crisis. https://www.governor.ny.gov/news/following-spike-domestic-violence-during-covid-19-pandemic-secretary-governor-melissa-derosa.Google Scholar
- Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global Vectors for Word Representation. In EMNLP. 1532–1543.Google Scholar
- Jim Samuel, GG Ali, Md Rahman, Ek Esawi, Yana Samuel, 2020. Covid-19 public sentiment insights and machine learning for tweets classification. Information 11, 6 (2020), 314.Google ScholarCross Ref
- Spotcrime. June, 2020. Daily Crime Blotter in Chicago. https://spotcrime.com/il/chicago/daily.Google Scholar
- Luan Tran, Xi Yin, and Xiaoming Liu. 2017. Disentangled representation learning gan for pose-invariant face recognition. In CVPR. 1415–1424.Google Scholar
- Twitter. 2020. Twitter API. https://developer.twitter.com/en/docs/tweets/search/api-reference/get-search-tweets.Google Scholar
- Vincent Van Asch. 2013. Macro-and micro-averaged evaluation measures [[basic draft]]. Belgium: CLiPS 49(2013).Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NIPS. 5998–6008.Google Scholar
- Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. 2016. Attention-based LSTM for aspect-level sentiment classification. In EMNLP. 606–615.Google Scholar
- WHO. 2020. Coronavirus disease (COVID-19). https://www.who.int/.Google Scholar
- Theresa Wilson, Janyce Wiebe, and Paul Hoffmann. 2005. Recognizing contextual polarity in phrase-level sentiment analysis. In EMNLP. 347–354.Google Scholar
- Rui Xia, Chengqing Zong, and Shoushan Li. 2011. Ensemble of feature sets and classification algorithms for sentiment classification. Information Sciences 181, 6 (2011), 1138–1152.Google ScholarDigital Library
- Hu Xu, Bing Liu, Lei Shu, and Philip S Yu. 2019. Bert post-training for review reading comprehension and aspect-based sentiment analysis. arXiv preprint arXiv:1904.02232(2019).Google Scholar
- Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In NIPS. 5753–5763.Google Scholar
- Yanfang Ye, Yujie Fan, Shifu Hou, Yiming Zhang, Yiyue Qian, Shiyu Sun, Qian Peng, Mingxuan Ju, Wei Song, and Kenneth Loparo. 2020. Community Mitigation: A Data-driven System for COVID-19 Risk Assessment in a Hierarchical Manner. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2909–2916.Google ScholarDigital Library
- Yanfang Ye, Shifu Hou, Yujie Fan, Yiming Zhang, Yiyue Qian, Shiyu Sun, Qian Peng, Mingxuan Ju, Wei Song, and Kenneth Loparo. 2020. a-Satellite: An AI-Driven System and Benchmark Datasets for Dynamic COVID-19 Risk Assessment in the United States. IEEE Journal of Biomedical and Health Informatics 24, 10(2020), 2755–2764.Google ScholarCross Ref
- Da Yin, Tao Meng, and Kai-Wei Chang. 2020. SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics. arXiv preprint arXiv:2005.04114(2020).Google Scholar
- Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. Character-level convolutional networks for text classification. In NIPS. 649–657.Google Scholar
- Dr.Emotion: Disentangled Representation Learning for Emotion Analysis on Social Media to Improve Community Resilience in the COVID-19 Era and Beyond
Recommendations
The bright and dark sides of social media use during COVID-19 lockdown: Contrasting social media effects through social liability vs. social support
AbstractThere exist ongoing discussions regarding whether, when, or why heightened reliance on social media becomes benefits or drawbacks, especially in times of crisis. Using the concepts of social liability, social support, and cognitive ...
Highlights- We examined when dependence on social media becomes promises or pitfalls.
- We ...
Moral Emotions Shape the Virality of COVID-19 Misinformation on Social Media
WWW '22: Proceedings of the ACM Web Conference 2022While false rumors pose a threat to the successful overcoming of the COVID-19 pandemic, an understanding of how rumors diffuse in online social networks is – even for non-crisis situations – still in its infancy. Here we analyze a large sample ...
Emotion Maps based on Geotagged Posts in the Social Media
GeoHumanities '17: Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial HumanitiesEmotions influence people's behavior in a profound way. Feelings like happiness, hope, fear, boredom, anger, anxiety or relaxation affect the way people behave and interact with one another. However, there is often a strong correlation between the ...
Comments