Elamur Research⌕
☰
home / papers / 2016 / Annotating Sentiment and Irony in the Online Italian Political Debate on #labuonascuola

Annotating Sentiment and Irony in the Online Italian Political Debate on #labuonascuola

Summary

The authors build TW-BS (TWitterBuonaScuola), a new Italian sentiment analysis resource. It focuses on the 2014 Twitter debate over "La Buona Scuola," the Renzi government's controversial school reform. They chose this reform because its hashtag was the most popular of the three big 2014 reform hashtags. They collected tweets using #labuonascuola and related keywords, removed retweets and near-duplicates, and annotated each message for sentiment polarity and irony. The scheme is compatible with the SENTIPOLC format and also labels which aspect (topic) of the reform a tweet addresses. For comparison, they gathered WEB-BS, a set of posts from the government's own online consultation site, which contributors had already tagged with stance and topic. The paper also analyzes inter-annotator disagreement, including tests on the Crowdflower platform. Irony and the neutral NONE label proved hardest to agree on. In TW-BS, negative tweets outnumber positive ones about threefold, and many criticisms are ironic. The consultation posts are more constructive and almost free of irony. The resource supports aspect-level and stance-oriented analysis of political debate.

Key points

  • Twitter data (TW-BS): 35,148 tweets matched the filters for 3 September to 15 November 2014. After automatic and manual deduplication, 8,594 remained.
  • Label distribution in TW-BS:
    • NONE: 3,177
    • NEG: 1,951
    • POS: 756
    • HUM NEG: 655
    • MIX: 92
    • HUM POS: 28
  • Consultation data (WEB-BS): 4,129 posts from labuonascuola.gov.it, labelled by contributors as:
    • 'what I like': 642
    • 'what I don't like': 892
    • 'what is missing': 675
    • 'new integration': 1,920
  • Topic findings: About 80% of the 5,573 topic-agreed tweets received only the generic tag. Topic distributions differ between the sources: evaluation dominates WEB-BS, while recruitment is frequent on Twitter.
  • User activity: In TW-BS, 20% of users produced roughly 60% of tweets, which is less skewed than the 80/20 Pareto pattern.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

12 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 9 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{stranisci2016annotating,
  title = {{Annotating Sentiment and Irony in the Online Italian Political Debate on \#labuonascuola}},
  author = {Stranisci, Marco and Bosco, Cristina and Farías, Delia Irazú Hernández and Patti, Viviana},
  booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)},
  year = {2016},
  doi = {10.63317/4abqh39vt3ni},
  url = {https://doi.org/10.63317/4abqh39vt3ni}
}

References

25 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Attardi, G., Basile, V., Bosco, C., Caselli, T., Dell’Orletta, F., Montemagni, S., Patti, V., Simi, M., and Sprugnoli, R. (2015). State of the art language technologies for italian: The EVALITA 2014 perspective. Journal of Intelligenza Artificiale, 9(1):43–61. find
  2. Basile, V. and Nissim, M. (2013). Sentiment analysis on italian tweets. In Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 100–107, Atlanta, Georgia. Association for Computational Linguistics. find
  3. Basile, V., Bolioli, A., Nissim, M., Patti, V., and Rosso, P. (2014a). find
  4. Evalita 2014 Sentipolc task: Task guidelines. Technical report. find
  5. Basile, V., Bolioli, A., Nissim, M., Patti, V., and Rosso, P. (2014b). Overview of the Evalita 2014 SENTIment POLarity Classification Task. In Proceedings of the 4th evaluation campaign of Natural Language Processing and Speech tools for Italian (EVALITA’14), pages 50–57, Pisa, Italy. find
  6. Pisa University Press. Bosco, C., Patti, V., and Bolioli, A. (2013). Developing corpora for sentiment analysis: The case of irony and Senti–TUT. IEEE Intelligent Systems, 28(2):55–63. find
  7. Bosco, C., Allisio, L., Mussa, V., Patti, V., Ruffo, G., Sanguinetti, M., and Sulis, E. (2014). Detecting happiness in italian tweets: Towards an evaluation dataset for sentiment analysis in Felicittà. In Proc. of the 5th International Workshop on Emotion, Social Signals, Sentiment and Linked Opena… find
  8. ELRA. Bosco, C., Patti, V., and Bolioli, A. (2015a). Developing corpora for sentiment analysis: The case of irony http://alt.qcri.org/semeval2016/task6/and senti-tut (extended abstract). In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI 2015, Buenos… ↗
  9. Bosco, C., Patti, V., Lai, M., and Virone, D. (2015b). Building a corpus on a debate on political reform in Twitter. In Proceedings of Second Italian Conference on Computational Linguistics, CLIC-it 2015, pages 171– 176, Trento, Italy. find
  10. Accademia University Press. Boyd, D. (2014). It’s Complicated: the social lives of networked teens. find
  11. Yale University Press. Ceron, A., Curini, L., and Stefano, I. M. (2014). Social Media e Sentiment Analysis: l’evoluzione dei fenomeni sociali attraverso la rete. find
  12. Springer. Conoscenti, M. (2011). The Reframer: An Analysis of Barack Obama Political Discourse (2004-2010). Bul-zoni Editore. Conover, M., Gonçalves, B., and Ratkiewicz, J. (2011). Predicting the political alignment of twitter users. In Proceeding of the IEEE Third Inernational Conference on Social… find
  13. Ghosh, A., Li, G., Veale, T., Rosso, P., Shutova, E., Barnden, J., and Reyes, A. (2015). Semeval-2015 task 11: Sentiment analysis of figurative language in twitter. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 470–478, Denver, Colorado, June. Associat… find
  14. Gloor, P., Krauss, J., Nann, S., Fischbach, K., and Schoder, D. (2009). Web science 2.0: Identifying trends through semantic social network analysis. In Proceedings of IEEE International Conference on Computational Science and Engineering (CSE-09), volume 4, pages 215– 222, Vancouver, Canada. find
  15. IEEE Computer Society. Karoui, J., Farah, B., Moriceau, V., Aussenac-Gilles, N., and Hadrich-Belguith, L. (2015). Towards a contextual pragmatic model to detect irony in tweets. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint… find our card
  16. Lai, M., Virone, D., Bosco, C., and Patti, V. (2015). Debate on political reforms in Twitter: A hashtag-driven analysis of political polarization. In Proc. of 2015 IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA’2015), Special Track on Emotion and Sentiment in Intelli… find
  17. IEEE. Maynard, D. and Funk, A. (2011). Automatic detection of political opinions in tweets. In Extended Semantic Web Conference Workshop, pages 88–99. find
  18. Maynard, D. and Greenwood, M. (2014). Who cares about sarcastic tweets? investigating the impact of sarcasm on sentiment analysis. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), Reykjavik, Iceland, may. find our card
  19. ELRA. Rajadesingan, A. and Liu, H. (2014). Identifying users with opposing opinions in twitter debates. In William G. Kennedy, et al., editors, Social Computing, Behavioral-Cultural Modeling and Prediction, volume 8393 of Lecture Notes in Computer Science, pages 153–160. find
  20. Springer International Publishing. Reyes, A. and Rosso, P. (2014). On the difficulty of automatically detecting irony: beyond a simple case of negation. Knowledge and Information Systems, 40(3):595– 614. find
  21. Reyes, A., Rosso, P., and Veale, T. (2013). A multidimensional approach for detecting irony in twitter. Language Resources and Evaluation, 47(1):239–268. find
  22. Sang, E. T. K. and Bos, J. (2012). Predicting the 2011 dutch senate election results with twitter. In Proceedings of the Workshop on Semantic Analysis in Social Media, pages 53–60, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  23. Sperber, D. and Wilson, D. (1986). Relevance: communication and cognition. Basil Blackwell. Stranisci, M., Bosco, C., Viviana, P., and Hernández Farias, D. I. (2015). Analyzing and annotating for sentiment analysis the socio-political debate on “La Buona Scuola”. In Proceedings of the 2th Italian C… find
  24. Accademia University Press. In Press. Tumasjan, A., Sprenger, T. O., Sandner, P. G., and Welpe, I. M. (2011). Predicting elections with Twitter: What 140 characters reveal about political sentiment. In Proceedings of the ICWSM-11, pages 178–185, Barcelona, Spain. find
  25. Wilson, D. (2006). The pragmatics of verbal irony: Echo or pretence? Lingua, 116(10):1722–1743. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/stranisci-2016-annotating-sentiment-irony-online-italian/