Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text Data

Understanding a person’s mood and circumstances by way of sentiment or finer-grained emotion detection can play a significant role in AI systems and applications, such as in chat dialogue or reviews. Analysis of emotion from text typically requires specialized text or document understanding, and rec...

Full description

Saved in:
Bibliographic Details
Main Authors: Robert H. Frye, David C. Wilson
Format: Article
Language:English
Published: LibraryPress@UF 2022-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/130612
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735589937545216
author Robert H. Frye
David C. Wilson
author_facet Robert H. Frye
David C. Wilson
author_sort Robert H. Frye
collection DOAJ
description Understanding a person’s mood and circumstances by way of sentiment or finer-grained emotion detection can play a significant role in AI systems and applications, such as in chat dialogue or reviews. Analysis of emotion from text typically requires specialized text or document understanding, and recent work has focused on transformer learning approaches. Common models of these transformers (e.g. BERT, RoBERTa, ELECTRA, XLM-R, and XLNet) have been pre-trained using longer texts of well-written English; however, many application contexts align more directly with social media content or have a shorter format more akin to social media, where texts often bend or violate standard language conventions. To understand the applicability and tradeoffs among common transformers within such contexts, our research investigates accuracy and efficiency considerations in fine-tuning transformers for granular emotion detection in short-text data. This paper presents a comparative study investigating the performance of five common transformers as applied in the specific context of multi-category emotion detection in short-text Twitter data. The study explores different considerations for hyperparameter settings in this context. Results show significant fine-tuning benefits in comparison to recommended baselines for the approaches and provide guidance for fine-tuning to support fine-grained emotion detection in short texts.
format Article
id doaj-art-115ff24561904716afa3d54fa3d6de08
institution DOAJ
issn 2334-0754
2334-0762
language English
publishDate 2022-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-115ff24561904716afa3d54fa3d6de082025-08-20T03:07:32ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622022-05-013510.32473/flairs.v35i.13061266811Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text DataRobert H. Frye0David C. WilsonUniversity of North Carolina at CharlotteUnderstanding a person’s mood and circumstances by way of sentiment or finer-grained emotion detection can play a significant role in AI systems and applications, such as in chat dialogue or reviews. Analysis of emotion from text typically requires specialized text or document understanding, and recent work has focused on transformer learning approaches. Common models of these transformers (e.g. BERT, RoBERTa, ELECTRA, XLM-R, and XLNet) have been pre-trained using longer texts of well-written English; however, many application contexts align more directly with social media content or have a shorter format more akin to social media, where texts often bend or violate standard language conventions. To understand the applicability and tradeoffs among common transformers within such contexts, our research investigates accuracy and efficiency considerations in fine-tuning transformers for granular emotion detection in short-text data. This paper presents a comparative study investigating the performance of five common transformers as applied in the specific context of multi-category emotion detection in short-text Twitter data. The study explores different considerations for hyperparameter settings in this context. Results show significant fine-tuning benefits in comparison to recommended baselines for the approaches and provide guidance for fine-tuning to support fine-grained emotion detection in short texts.https://journals.flvc.org/FLAIRS/article/view/130612transformershyperparametersemotion detectionfine-grained emotion detectionfine-tuning
spellingShingle Robert H. Frye
David C. Wilson
Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text Data
Proceedings of the International Florida Artificial Intelligence Research Society Conference
transformers
hyperparameters
emotion detection
fine-grained emotion detection
fine-tuning
title Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text Data
title_full Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text Data
title_fullStr Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text Data
title_full_unstemmed Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text Data
title_short Comparative Analysis of Transformers to Support Fine-Grained Emotion Detection in Short-Text Data
title_sort comparative analysis of transformers to support fine grained emotion detection in short text data
topic transformers
hyperparameters
emotion detection
fine-grained emotion detection
fine-tuning
url https://journals.flvc.org/FLAIRS/article/view/130612
work_keys_str_mv AT roberthfrye comparativeanalysisoftransformerstosupportfinegrainedemotiondetectioninshorttextdata
AT davidcwilson comparativeanalysisoftransformerstosupportfinegrainedemotiondetectioninshorttextdata