Hybrid Transformer Learning with Contextual Semantic Features for Sarcasm Detection
International Journal of Drug Delivery Technology · 16.11.2026 · 16 (80s)
DOI: 10.25258/ijddt.16.80s.70 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 16.11.2026. Verfasst von Yuvraj G. Nikam und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Sarcasm detection is a challenging problem in computational linguistics because the sentiment expressed on the surface of a sarcastic utterance frequently contradicts the sentiment its author intends. Existing detectors are also brittle: models that perform well on one platform typically degrade sharply when applied to text from a different domain or writing style. This paper proposes a context-aware hybrid model that couples a pre-trained BERT encoder with a bidirectional LSTM and an additive attention layer, and fuses the resulting contextual representation with two complementary signals — an unsupervised topic-context vector obtained from BERTopic and a set of nine handengineered linguistic cues. The model is trained only on a labelled Twitter corpus and evaluated in two regimes: an in-domain held-out Twitter test set and a zero-shot cross-domain test on a balanced, formally-written News-Headlines corpus that the model never sees during training. Against four classical TF-IDF baselines and pure transformer baselines evaluated under an identical protocol, the proposed hybrid attains the strongest in-domain results, reaching an accuracy of 0.8695 and an F1-score of 0.7945, and the zero-shot cross-domain evaluation quantifies the extent to which a tweet-trained detector generalizes to a different register. The results indicate that combining a contextual transformer encoder with unsupervised topic context and linguistic cues is an effective and transferable design for sarcasm detection.
Zitieren
APA
Nikam, Y. G., Singh, V. P., & Shinde, D. A. (2026). Hybrid Transformer Learning with Contextual Semantic Features for Sarcasm Detection. International Journal of Drug Delivery Technology, 16(80s). https://doi.org/10.25258/ijddt.16.80s.70
Vancouver
Nikam YG, Singh VP, Shinde DA. Hybrid Transformer Learning with Contextual Semantic Features for Sarcasm Detection. International Journal of Drug Delivery Technology. 2026;16(80s). doi:10.25258/ijddt.16.80s.70
BibTeX
@article{Nikam2026,
author = {Nikam, Yuvraj G. and Singh, Vijay Pal and Shinde, Dhanshri Amol},
title = {Hybrid Transformer Learning with Contextual Semantic Features for Sarcasm Detection},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {80s},
doi = {10.25258/ijddt.16.80s.70}
}
EUVIMED