Embracing emojis in sarcasm detection to enhance sentiment analysis
Embracing emojis in sarcasm detection to enhance sentiment analysis
Emojis are commonly used in social media posts to express sentiment. Most NLP studies clean their text from emojis in the pre-processing stage. This study suggests a framework to analyze sentiment and detect sarcasm by using the Emoji Dictionary (ED) and Sarcasm Detection Approach (SDA) with VADER as a lexicon-based classifier and BERT as a machine learning model to examine the impact of emojis on sentiment classification performance and in detecting sarcasm on three different topic datasets. The study's finding is that keeping emojis, using the ED, and a proposed SDA approach have an effect on increasing classification performance.
sentiment analysis, sarcasm detection, emojis
Alsabban, Malak Abdullah
c5a89acb-c4ac-4da0-aee6-12bbfa424850
Weal, Mark
e8fd30a6-c060-41c5-b388-ca52c81032a4
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c
Alsabban, Malak Abdullah
c5a89acb-c4ac-4da0-aee6-12bbfa424850
Weal, Mark
e8fd30a6-c060-41c5-b388-ca52c81032a4
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c
Alsabban, Malak Abdullah, Weal, Mark and Hall, Wendy
(2024)
Embracing emojis in sarcasm detection to enhance sentiment analysis.
International Conference on Computer & Applications, BUE, El Shorouk, Egypt.
17 - 19 Dec 2024.
7 pp
.
(In Press)
Record type:
Conference or Workshop Item
(Paper)
Abstract
Emojis are commonly used in social media posts to express sentiment. Most NLP studies clean their text from emojis in the pre-processing stage. This study suggests a framework to analyze sentiment and detect sarcasm by using the Emoji Dictionary (ED) and Sarcasm Detection Approach (SDA) with VADER as a lexicon-based classifier and BERT as a machine learning model to examine the impact of emojis on sentiment classification performance and in detecting sarcasm on three different topic datasets. The study's finding is that keeping emojis, using the ED, and a proposed SDA approach have an effect on increasing classification performance.
Text
ICCA paper
- Accepted Manuscript
Restricted to Registered users only
Request a copy
More information
Accepted/In Press date: 1 September 2024
Venue - Dates:
International Conference on Computer & Applications, BUE, El Shorouk, Egypt, 2024-12-17 - 2024-12-19
Keywords:
sentiment analysis, sarcasm detection, emojis
Identifiers
Local EPrints ID: 494855
URI: http://eprints.soton.ac.uk/id/eprint/494855
PURE UUID: 59031030-c656-425d-bf87-c36f0a4b697f
Catalogue record
Date deposited: 17 Oct 2024 16:46
Last modified: 18 Oct 2024 01:33
Export record
Contributors
Author:
Malak Abdullah Alsabban
Author:
Mark Weal
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics