Comparative Study of Pre-trained Language Models for Text Classification in Smart Agriculture Domain

Yadav, Sargam; Kaushik, Abhishek

doi:10.1007/978-981-99-0981-0_21

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are studies that conclude the superiority of BERT in different text classification tasks. One study was from Yadav et al ( 2023) [17] where they examine how people perceive smart farming technologies by conducting sentiment analysis on data extracted from YouTube using 3 transformer models: GPT-2, BERT specifically fine-tuned for the agricultural domain, and a BERT variant, DistilBERT. The study's findings and statistical evaluations suggest that transformer models are effective for categorizing both technical and agricultural texts.…”

Section: Related Studiesmentioning

confidence: 99%

Fine-tuning Pre-trained Language Models to Detect In-game Trash Talks

et al. 2024

IJFMR

View full text Add to dashboard Cite

Common problems in playing online mobile and computer games were related to toxic behavior and abusive communication among players. Based on different reports and studies, the study also discusses the impact of online hate speech and toxicity on players' in-game performance and overall well-being. This study investigates the capability of pre-trained language models to classify or detect trash talk or toxic in-game messages. The study employs and evaluates the performance of pre-trained BERT and GPT language models in detecting toxicity within in-game chats. Using publicly available APIs, in-game chat data from DOTA 2 game matches were collected, processed, reviewed, and labeled as non-toxic, mild (toxicity), and toxic. The study was able to collect around two thousand in-game chats to train and test BERT (Base-uncased), BERT (Large-uncased), and GPT-3 models. Based on the three models’ state-of-the-art performance, this study concludes pre-trained language models’ promising potential for addressing online hate speech and in-game insulting trash talk.

show abstract

Section: Related Studiesmentioning

confidence: 99%