Multi-task dialog act and sentiment recognition on Mastodon

Abstract : Because of license restrictions, it often becomes impossible to strictly reproduce most research results on Twitter data already a few months after the creation of the corpus. This situation worsened gradually as time passes and tweets become inaccessible. This is a critical issue for reproducible and accountable research on social media. We partly solve this challenge by annotating a new Twitter-like corpus from an alternative large social medium with licenses that are compatible with reproducible experiments: Mastodon. We manually annotate both dialogues and sentiments on this corpus, and train a multi-task hierarchical recurrent network on joint sentiment and dialog act recognition. We experimentally demonstrate that transfer learning may be efficiently achieved between both tasks, and further analyze some specific correlations between sentiments and dialogues on social media. Both the annotated corpus and deep network are released with an open-source license.
Liste complète des métadonnées

Cited literature [7 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01838323
Contributor : Christophe Cerisara <>
Submitted on : Friday, July 13, 2018 - 11:36:58 AM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Document(s) archivé(s) le : Monday, October 15, 2018 - 11:43:57 AM

Files

dasent.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01838323, version 1
  • ARXIV : 1807.05013

Citation

Christophe Cerisara, Somayeh Jafaritazehjani, Adedayo Oluokun, Hoa Le. Multi-task dialog act and sentiment recognition on Mastodon. COLING, Aug 2018, Santa Fe, United States. ⟨hal-01838323⟩

Share

Metrics

Record views

129

Files downloads

96