Emotional reactions to Online Social Network posts have recently gained importance in the study of the online ecosystem. Prior to post publication, the number of received reactions can be predicted based on either the textual content of the post or the related metadata. However, existing approaches suffer from both the lack of semantic-aware language understanding models and the limited explainability of the prediction models. To overcome these issues, we present a new transformer-based method to predict the number of emotional reactions of different types to social posts. It leverages the attention mechanism to capture arbitrary semantic textual relations neglected by prior works. Furthermore, it also provides end-users with textual explanations of the predictions. The results achieved on a large collection of Facebook posts confirm the applicability of the presented methodology.
Transformer-based Prediction of Emotional Reactions to Online Social Network Posts / Benedetto, Irene; La Quatra, Moreno; Cagliero, Luca; Vassio, Luca; Trevisan, Martino. - ELETTRONICO. - (2023), pp. 354-364. (Intervento presentato al convegno Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA) tenutosi a Toronto (CAN) nel July 9–14, 2023) [10.18653/v1/2023.wassa-1.31].
Transformer-based Prediction of Emotional Reactions to Online Social Network Posts
Benedetto, Irene;La Quatra, Moreno;Cagliero, Luca;Vassio, Luca;Trevisan, Martino
2023
Abstract
Emotional reactions to Online Social Network posts have recently gained importance in the study of the online ecosystem. Prior to post publication, the number of received reactions can be predicted based on either the textual content of the post or the related metadata. However, existing approaches suffer from both the lack of semantic-aware language understanding models and the limited explainability of the prediction models. To overcome these issues, we present a new transformer-based method to predict the number of emotional reactions of different types to social posts. It leverages the attention mechanism to capture arbitrary semantic textual relations neglected by prior works. Furthermore, it also provides end-users with textual explanations of the predictions. The results achieved on a large collection of Facebook posts confirm the applicability of the presented methodology.File | Dimensione | Formato | |
---|---|---|---|
2023.wassa-1.31.pdf
accesso aperto
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Creative commons
Dimensione
359.41 kB
Formato
Adobe PDF
|
359.41 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2982615