--- title: "Towards Sentiment and Emotion aided Multi-modal Speech Act" description: "They build EmoTA, a subset of 6810 tweets drawn from SemEval-2018. 68.57 accuracy. 36 references, cited by 11 papers here." authors: ["Tulika Saha", "Apoorva Upadhyaya", "Sriparna Saha", "Pushpak Bhattacharyya"] year: 2021 venue: "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies" source: "https://aclanthology.org/2021.naacl-main.456/" doi: "10.18653/v1/2021.naacl-main.456" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/saha-2021-sentiment-emotion-aided-multi-modal/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/saha-2021-sentiment-emotion-aided-multi-modal/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/5/) / Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter # Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter **Authors:** [Tulika Saha](https://md.research.elamur.ai/free/en/authors/tulika-saha/), Apoorva Upadhyaya, [Sriparna Saha](https://md.research.elamur.ai/free/en/authors/sriparna-saha/) and [Pushpak Bhattacharyya](https://md.research.elamur.ai/free/en/authors/pushpak-bhattacharyya/) · **Year:** 2021 · **Venue:** [Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2021](https://md.research.elamur.ai/free/en/venues/naacl/2021/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2021.naacl-main.456/) · [PDF](https://aclanthology.org/2021.naacl-main.456.pdf) · [DOI 10.18653/v1/2021.naacl-main.456](https://doi.org/10.18653/v1/2021.naacl-main.456) · [OpenAlex](https://openalex.org/W3169111764) **Citations:** 32 citations (OpenAlex, 2026-10-14) · [11](https://md.research.elamur.ai/free/en/papers/saha-2021-sentiment-emotion-aided-multi-modal/cited-by/) in our library, of the 141,840 papers whose bibliographies we read ## Summary The paper addresses tweet act classification (TAC), which means identifying the speech act behind a tweet, such as a statement, question, request or threat. Earlier work handled TAC in isolation and on text alone. The authors argue that the writer's sentiment and emotion carry useful signal about intent, and that emojis add a nonverbal channel. They build EmoTA, a subset of 6810 tweets drawn from SemEval-2018. These tweets already had multi-label emotion tags, and the authors manually added tweet act labels and machine-derived (silver) sentiment labels. Their model is a multi-task, adversarially trained network built around a Dyadic Attention Mechanism (DAM). DAM attends within each modality (text, emoji) and across modalities. TAC is the main task, and Sentiment Analysis and Emotion Recognition serve as helper tasks. The joint multi-modal setup consistently beats single-task and text-only versions and outperforms re-implemented earlier TAC systems on EmoTA. The work matters because it shows that affective signals can help recover pragmatic intent in short, noisy social-media text. ## Key points - EmoTA: 6810 tweets, each with text and emoji as separate modalities. Labels cover 7 tweet act tags (sta, exp, que, req, sug, tht, oth), 11 multi-label emotion categories from SemEval-2018, and 3 sentiment tags. - Three annotators trained in English linguistics labelled the tweet acts without seeing the emotion tags. Reliable agreement was set above 80%. Sentiment came from the IBM Watson classifier as silver labels. - On the proposed model, a shared-private (SP) multi-task design worked better than a fully shared (FS) one, and adding an adversarial loss helped further. BERT text features outperformed GloVe. - The proposed model reached 68.57 accuracy and 66.15 F1, against 67.10 / 65.00 for the strongest earlier TAC model re-implemented on EmoTA. Gains were checked with Welch's test. - Adding emotion as a helper task gave larger gains than adding sentiment. Errors concentrated on rare classes (req, tht), on overlapping tags (sug mislabelled as exp), and on the shapeless "oth" class. The 5-class setup scored better than the 7-class setup. ## Interesting ideas - Use the writer's affective state as an auxiliary prediction target, not just an input feature, so that intent recognition picks up correlated cues; fine-grained emotion helped more than coarse polarity. - Annotators labelled speech acts without seeing the existing emotion tags, which prevents the two label layers from leaking into each other and creating artificial correlations. - Treat emojis as their own modality with separate attention instead of flattening them into the word stream, and compare both options. - Keep task-specific (private) parameters next to shared ones and add an adversarial loss so the shared space stays task-neutral; this suits weakly related tasks better than full sharing. - The error analysis groups confusions by structural causes: class imbalance, tags that subsume one another, and a catch-all class with no pattern. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (frames): The speech-act module in prag could jointly infer an emotion/attitude slot for the speaker and use it as evidence when choosing between expression, suggestion and threat readings. - **I2** (learn): When the LLM teacher or human annotators add a new label layer to silver data, hide the correlated layers from them, so that any agreement measured between layers is genuine. - **I3** (tokens): The tokenizer could tag emojis and similar nonverbal symbols as a distinct token class carrying attitude features, rather than treating them as unknown punctuation. - **I4** (learn): When gparse is trained alongside auxiliary heads such as tagging or role labelling, a shared-private split could stop weakly related heads from degrading the parser. - **I5** (frames): Audit the speech-act tag set for nested or catch-all categories and split or redefine them, so that each act has explainable, checkable criteria. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [Indian Institute of Technology Patna](https://md.research.elamur.ai/free/en/universities/indian-institute-of-technology-patna/) — University, Patna, India · 10 works · 262 citations 📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 798 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 463 works 🧭 Topics (3): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 609 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 269 works · [💬 Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · 160 works ## Cite Cite as: Tulika Saha, Apoorva Upadhyaya, Sriparna Saha and Pushpak Bhattacharyya. 2021. Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{saha2021sentiment, title = {{Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter}}, author = {Tulika Saha, Apoorva Upadhyaya, Sriparna Saha and Pushpak Bhattacharyya}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies}, year = {2021}, doi = {10.18653/v1/2021.naacl-main.456}, url = {https://doi.org/10.18653/v1/2021.naacl-main.456} } ``` - [← previous Speaker Turn Modeling for Dialogue Act Classification](https://md.research.elamur.ai/free/en/papers/he-2021-speaker-turn-modeling-dialogue-act/) - [next → What Does Your Smile Mean? Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probability](https://md.research.elamur.ai/free/en/papers/liu-2021-what-does-your-smile-mean/) - [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/5/) ## References 36 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Samuel Albanie, Arsha Nagrani, Andrea Vedaldi, and Andrew Zisserman. 2018. Emotion recognition in speech using cross-modal transfer in the wild. In Proceedings of the 26th ACM international conference on Multimedia, pages 292–301. Lisa Feldman. [↗](https://doi.org/10.48550/arxiv.1808.05561) 2. Barrett, Michael Lewis, and Jeannette M. Haviland-Jones. 1993. Handbook of emotions. The Guilford Press. [find](https://scholar.google.com/scholar?q=Barrett%2C+Michael+Lewis%2C+and+Jeannette+M%2E+Haviland%2DJones%2E+1993%2E+Handbook+of+emotions%2E+The+Guilford+Press%2E) 3. Christos Baziotis, Nikos Pelekis, and Christos Doulk-eridis. 2017. [Datastories at semeval-2017 task 4: Deep lstm with attention for message-level and topic-based sentiment analysis](https://md.research.elamur.ai/free/en/papers/baziotis-2017-datastories-semeval-2017-task-4/). In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 747–754, Vancouver, Canada. Association for Computational Linguistics. 4. Christophe Cerisara, Somayeh Jafaritazehjani, Ade-dayo Oluokun, and Hoa Le. 2018. [Multi-task dialog act and sentiment recognition on mastodon](https://md.research.elamur.ai/free/en/papers/cerisara-2018-multi-task-dialog-act-sentiment/). arXiv preprint arXiv:1807.05013. [↗](https://arxiv.org/abs/1807.05013) 5. In this paper, we studied the role of sentiment Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: pre-training of and emotion in speech act classification in Twit-deep bidirectional transformers for language under-ter. We curate a novel dataset EmoTA, that con-standing. In Proceedings of the 2019 Conference tains pre-annotated tweets with emotions collected of the North American Chapter of the Association from open-source dataset and annotated with TAs for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, and sentiment categories. We propose a Dyadic USA, June 2-7, 2019, Volume 1 (Long and Short Pa-Attention Mechanism based multi-modal (emojis pers), pages 4171–4186. and text), adversarial multi-task framework for joint optimization of TAs, sentiment and emo- Hai Ha Do, PWC Prasad, Angelika Maag, and Abeer Alsadoon. 2019. Deep learning for aspect-based sen-tions. The DAM (dyadic attention mechanism) timent analysis: a comparative review. Expert Sys-module employs intra-modal and inter-modal at-tems with Applications, 118:272–299. tention to fuse multiple modalities and learn generalized features across all the tasks. Results show Ben Eisner, Tim Rocktäschel, Isabelle Augenstein, Matko Bosnjak, and Sebastian Riedel. 2016. that multi-modality and multi-tasking boosted the emoji2vec: Learning emoji representations from performance of TA identification compared to its their description. In Proceedings of The Fourth In-uni-modal and single task TAC variants. ternational Workshop on Natural Language Process-In future, attempts will be made to predict TAs ing for Social Media, SocialNLP@EMNLP 2016, Austin, TX, USA, November 1, 2016, pages 48–54. with more precision by incorporating fine-grained Association for Computational Linguistics. modality encodings and also identifying which other NLP tasks (e.g., named entity recognition) Paul Ekman. 1999. Basic emotions. Handbook of cog-might assist TAC as a task. nition and emotion, 98(45-60):16. 5735 [find](https://scholar.google.com/scholar?q=In+this+paper%2C+we+studied+the+role+of+sentiment+Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+pre%2Dtraining+of+and+emotion+in+speech+act+classification+in+Twit%2Ddeep+bidi) 6. Bjarke Felbo, Alan Mislove, Anders Søgaard, Iyad Rahwan, and Sune Lehmann. 2017. [Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm](https://md.research.elamur.ai/free/en/papers/felbo-2017-millions-emoji-occurrences-learn-any/). In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, pages 1615–1625. Association for Computational Linguistics. 7. Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In International conference on machine learning, pages 1180–1189. PMLR. [↗](https://doi.org/10.48550/arxiv.1409.7495) 8. Alec Go, Richa Bhayani, and Lei Huang. 2009. Twitter sentiment classification using distant supervision. CS224N project report, Stanford, 1(12):2009. [find](https://scholar.google.com/scholar?q=Alec+Go%2C+Richa+Bhayani%2C+and+Lei+Huang%2E+2009%2E+Twitter+sentiment+classification+using+distant+supervision%2E+CS224N+project+report%2C+Stanford%2C+1%2812%29%3A2009%2E) 9. John J Godfrey, Edward C Holliman, and Jane Mc-Daniel. 1992. Switchboard: Telephone speech corpus for research and development. In Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., 1992 IEEE International Conference on, volume 1, pages 517–520. IEEE. [↗](https://doi.org/10.1109/icassp.1992.225858) 10. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780. [↗](https://doi.org/10.1162/neco.1997.9.8.1735) 11. M Shamim Hossain and Ghulam Muhammad. 2019. Emotion recognition using deep learning approach from audio–visual emotional big data. Information Fusion, 49:69–78. [↗](https://doi.org/10.1016/j.inffus.2018.09.008) 12. Minwoo Jeong, Chin-Yew Lin, and Gary Geunbae Lee. 2009. Semi-supervised speech act recognition in emails and forums. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3-Volume 3, pages 1250–1259. Association for Computational Linguistics. of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012), pages 246–255. [find](https://scholar.google.com/scholar?q=Minwoo+Jeong%2C+Chin%2DYew+Lin%2C+and+Gary+Geunbae+Lee%2E+2009%2E+Semi%2Dsupervised+speech+act+recognition+in+emails+and+forums%2E+In+Proceedings+of+the+2009+Conference+on+Empirical+Methods+in+Natural+Language+Proc) 13. Saif Mohammad, Felipe Bravo-Marquez, Mohammad Salameh, and Svetlana Kiritchenko. 2018. [Semeval-2018 task 1: Affect in tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2018-semeval-2018-task-1-affect/). In Proceedings of the 12th international workshop on semantic evaluation, pages 1–17. 14. Saif Mohammad and Svetlana Kiritchenko. 2018. Understanding emotions: A dataset of tweets to study interactions between affect categories. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). [find](https://scholar.google.com/scholar?q=Saif+Mohammad+and+Svetlana+Kiritchenko%2E+2018%2E+Understanding+emotions%3A+A+dataset+of+tweets+to+study+interactions+between+affect+categories%2E+In+Proceedings+of+the+Eleventh+International+Conference+on+La) 15. Saif M Mohammad and Peter D Turney. 2013. Crowdsourcing a word–emotion association lexicon. Computational Intelligence, 29(3):436–465. [↗](https://doi.org/10.1111/j.1467-8640.2012.00460.x) 16. Obrahim Oleri and Pinar Karagoz. 2016. Detecting user emotions in twitter through collective classification. In KDIR, pages 205–212. [find](https://scholar.google.com/scholar?q=Obrahim+Oleri+and+Pinar+Karagoz%2E+2016%2E+Detecting+user+emotions+in+twitter+through+collective+classification%2E+In+KDIR%2C+pages+205%E2%80%93212%2E) 17. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. [Glove: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543. [↗](https://doi.org/10.3115/v1/d14-1162) 18. Robert Plutchik. 1980. A general psychoevolutionary theory of emotion. In Theories of emotion, pages 3–33. Elsevier. [↗](https://doi.org/10.1016/b978-0-12-558701-3.50007-7) 19. Tulika Saha, Dhawal Gupta, Sriparna Saha, and Pushpak Bhattacharyya. 2021. Emotion aided dialogue act classification for task-independent conversations in a multi-modal framework. Cognitive Computation, 13(2):277–289. [↗](https://doi.org/10.1007/s12559-019-09704-5) 20. Abhishek Kumar, Asif Ekbal, Daisuke Kawahra, and Sadao Kurohashi. 2019. Emotion helps sentiment: A multi-task model for sentiment and emotion analysis. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE. [find](https://scholar.google.com/scholar?q=Abhishek+Kumar%2C+Asif+Ekbal%2C+Daisuke+Kawahra%2C+and+Sadao+Kurohashi%2E+2019%2E+Emotion+helps+sentiment%3A+A+multi%2Dtask+model+for+sentiment+and+emotion+analysis%2E+In+2019+International+Joint+Conference+on+Neural) 21. Tulika Saha, Srivatsa Ramesh Jayashree, Sriparna Saha, and Pushpak Bhattacharyya. 2020a. Bert-caps: A transformer-based capsule network for tweet act classification. IEEE Transactions on Computational Social Systems, 7(5):1168–1179. [↗](https://doi.org/10.1109/tcss.2020.3014128) 22. Pengfei Liu, Xipeng Qiu, and Xuanjing Huang. 2017. [Adversarial multi-task learning for text classification](https://md.research.elamur.ai/free/en/papers/liu-2017-adversarial-multi-task-learning-text/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 - August 4, Volume 1: Long Papers, pages 1–10. Association for Computational Linguistics. 23. Tulika Saha, Aditya Patra, Sriparna Saha, and Pushpak Bhattacharyya. 2020b. [Towards emotion-aided multi-modal dialogue act classification](https://md.research.elamur.ai/free/en/papers/saha-2020-emotion-aided-multi-modal-dialogue/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4361–4372. 24. Navonil Majumder, Soujanya Poria, Devamanyu Haz-arika, Rada Mihalcea, Alexander Gelbukh, and Erik Cambria. 2019. Dialoguernn: An attentive rnn for emotion detection in conversations. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 6818–6825. [↗](https://doi.org/10.1609/aaai.v33i01.33016818) 25. Saif Mohammad. 2012. [# emotional tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2012-emotional-tweets/). In * SEM 2012: The First Joint Conference on Lexical and Computational Semantics–Volume 1: Proceedings Tulika Saha, Aditya Prakash Patra, Sriparna Saha, and Pushpak Bhattacharyya. 2020c. A transformer based approach for identification of tweet acts. In 2020 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE. 26. Tulika Saha, Sriparna Saha, and Pushpak Bhattacharyya. 2019. Tweet act classification: A deep learning based classifier for recognizing speech acts in twitter. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE. [find](https://scholar.google.com/scholar?q=Tulika+Saha%2C+Sriparna+Saha%2C+and+Pushpak+Bhattacharyya%2E+2019%2E+Tweet+act+classification%3A+A+deep+learning+based+classifier+for+recognizing+speech+acts+in+twitter%2E+In+2019+International+Joint+Conference+o) 27. Ameneh Gholipour Shahraki and Osmar R Zaiane. 2017. Lexical and learning-based emotion mining from text. In Proceedings of the International Conference on Computational Linguistics and Intelligent Text Processing, volume 9, pages 24–55. [find](https://scholar.google.com/scholar?q=Ameneh+Gholipour+Shahraki+and+Osmar+R+Zaiane%2E+2017%2E+Lexical+and+learning%2Dbased+emotion+mining+from+text%2E+In+Proceedings+of+the+International+Conference+on+Computational+Linguistics+and+Intelligent+Tex) 28. Mohammad Soleymani, David Garcia, Brendan Jou, Björn Schuller, Shih-Fu Chang, and Maja Pantic. 2017. A survey of multimodal sentiment analysis. Image and Vision Computing, 65:3–14. [↗](https://doi.org/10.1016/j.imavis.2017.08.003) 29. Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Taylor, Rachel Martin, Carol Van Ess-Dykema, and Marie Meteer. 2000. [Dialogue act modeling for automatic tagging and recognition of conversational speech](https://md.research.elamur.ai/free/en/papers/stolcke-2000-dialogue-act-modeling-automatic-tagging/). Computational linguistics, 26(3):339–373. [↗](https://doi.org/10.1162/089120100561737) 30. Mike Thelwall, Kevan Buckley, and Georgios Pal-toglou. 2012. Sentiment strength detection for the social web. Journal of the American Society for Information Science and Technology, 63(1):163–173. [↗](https://doi.org/10.1002/asi.21662) 31. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, pages 5998–6008. 32. Soroush Vosoughi. 2015. Automatic detection and verification of rumors on Twitter. Ph.D. thesis, Massachusetts Institute of Technology. [find](https://scholar.google.com/scholar?q=Soroush+Vosoughi%2E+2015%2E+Automatic+detection+and+verification+of+rumors+on+Twitter%2E+Ph%2ED%2E+thesis%2C+Massachusetts+Institute+of+Technology%2E) 33. Soroush Vosoughi and Deb Roy. 2016. [Tweet acts: A speech act classifier for twitter](https://md.research.elamur.ai/free/en/papers/vosoughi-2016-tweet-acts-speech-act-classifier/). In Tenth International AAAI Conference on Web and Social Media. [↗](https://doi.org/10.48550/arxiv.1605.05156) 34. Wenbo Wang, Lu Chen, Krishnaprasad Thirunarayan, and Amit P Sheth. 2012. Harnessing twitter" big data" for automatic emotion identification. In 2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing, pages 587–592. IEEE. [↗](https://doi.org/10.1109/socialcom-passat.2012.119">https://doi.org/10.1109/socialcom-passat.2012.119