Detection of Reading Absorption in User-Generated Book Reviews:Resources Creation and Evaluation - IMT Mines Alès
Communication Dans Un Congrès Année : 2020

Detection of Reading Absorption in User-Generated Book Reviews:Resources Creation and Evaluation

Résumé

To detect how and when readers are experiencing engagement with a literary work, we bring together empirical literary studies andlanguage technology via focusing on the affective state of absorption. The goal of our resource development is to enable the detectionof different levels of reading absorption in millions of user-generated reviews hosted on social reading platforms. We present a corpusof social book reviews in English that we annotated with reading absorption categories. Based on these data, we performed supervised,sentence level, binary classification of the explicit presence vs. absence of the mental state of absorption. We compared the performancesof classical machine learners where features comprised sentence representations obtained from a pretrained embedding model (UniversalSentence Encoder) vs. neural classifiers in which sentence embedding vector representations are adapted or fine-tuned while trainingfor the absorption recognition task. We discuss the challenges in creating the labeled data as well as the possibilities for releasing a benchmark corpus.
Fichier principal
Vignette du fichier
2020.lrec-1.595.pdf (1.74 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02868319 , version 1 (15-06-2020)

Identifiants

  • HAL Id : hal-02868319 , version 1

Citer

Piroska Lendvai, Sándor Darányi, Christian Geng, Moniek Kuijper, Oier Lopez de Lacalle, et al.. Detection of Reading Absorption in User-Generated Book Reviews:Resources Creation and Evaluation. LREC 2020 - 12th Conference on Language Resources and Evaluation, 2020, Marseille, France. pp.4835-4841. ⟨hal-02868319⟩
253 Consultations
219 Téléchargements

Partager

More