Give me your Intentions, I’ll Predict our Actions: A Two-level Classification of Speech Acts for Crisis Management in Social Media

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 4333–4343 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 4333 Give me your Intentions, I’ll Predict Our Actions: A Two-level Classification of Speech Acts for Crisis Management in Social Media Enzo Laurenti1, Nils Bourgon2, Farah Benamara2, Alda Mari1, V´eronique Moriceau2, Camille Courgeon1 1 IJN, CNRS/ENS/EHESS/PSL University {firstname.lastname@ens.fr} 2 IRIT, Universit´e de Toulouse, CNRS, Toulouse INP, UT3, Toulouse, France {firstname.lastname@irit.fr} Abstract Discovered by (Austin,1962) and extensively promoted by (Searle, 1975), speech acts (SA) have been the object of extensive discussion in the philosophical and the linguistic literature, as well as in computational linguistics where the detection of SA have shown to be an important step in many down stream NLP applications. In this paper, we attempt to measure for the first time the role of SA on urgency detection in tweets, focusing on natural disasters. Indeed, SA are particularly relevant to identify intentions, desires, plans and preferences towards action, providing therefore actionable information that will help to set priorities for the human teams and decide appropriate rescue actions. To this end, we come up here with four main contribu- tions: (1) A two-layer annotation scheme of SA both at the tweet and subtweet levels, (2) A new French dataset of 6,669 tweets annotated for both urgency and SA, (3) An in-depth analysis of the annotation campaign, highlighting the correlation between SA and urgency categories, and (4) A set of deep learning experiments to detect SA in a crisis corpus. Our results show that SA are correlated with urgency which is a first important step towards SA-aware NLP-based crisis management on social media. Keywords: Speech acts, Crisis events, Social Media 1. Introduction The use of social networks is pervasive in our daily life. All areas are concerned, including civil security and crisis management. Recently, Twitter has been widely used to generate valuable information in crisis situations, showing that traditional means of commu- nication between population and rescue departments (e.g., phone calls) are clearly suboptimal (Vieweg et al., 2014; Olteanu et al., 2015). For example, more than 20 million tweets were posted during the super- storm Sandy in 2012 (Castillo, 2016) and the hashtag #NotreDame relatif to the the Notre Dame fire that oc- curred in France has been the most used in Twitter in 2019.1 One crucial aspect of tweets posted during crisis events pertains to the fact that people express their intentions, desires, plans, goals and preferences towards action, providing therefore actionable information that will help to set priorities for the human teams and decide appropriate rescue actions. For example, in the tweet (1a),2 the writer publicly expresses an explicit commit- ment to provide help after the Irma hurricane tragedy, using an explicit action verb (“to help”) which is under the scope of an explicit attitude verb (“want”). (1b) on the other hand expresses an intention to complain about the absence of assistance without using any explicit in- tent keywords. Intention to advise, …

Content truncated to 500 words