Next Article in Journal
Determination of Main Bearing Dynamic Clearance in a Shield Tunneling Machine Through a Broadband PMUT Array with a Decreased Blind Area and High Accuracy
Previous Article in Journal
Mobile Tunnel Lining Measurable Image Scanning Assisted by Collimated Lasers
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Emoji-Driven Sentiment Analysis for Social Bot Detection with Relational Graph Convolutional Networks

College of Computer Science, Beijing University of Technology, Beijing 100124, China
*
Author to whom correspondence should be addressed.
Sensors 2025, 25(13), 4179; https://doi.org/10.3390/s25134179 (registering DOI)
Submission received: 13 May 2025 / Revised: 28 June 2025 / Accepted: 3 July 2025 / Published: 4 July 2025
(This article belongs to the Section Sensor Networks)

Abstract

The proliferation of malicious social bots poses severe threats to cybersecurity and social media information ecosystems. Existing detection methods often overlook the semantic value and emotional cues conveyed by emojis in user-generated tweets. To address this gap, we propose ESA-BotRGCN, an emoji-driven multi-modal detection framework that integrates semantic enhancement, sentiment analysis, and multi-dimensional feature modeling. Specifically, we first establish emoji–text mapping relationships using the Emoji Library, leverage GPT-4 to improve textual coherence, and generate tweet embeddings via RoBERTa. Subsequently, seven sentiment-based features are extracted to quantify statistical disparities in emotional expression patterns between bot and human accounts. An attention gating mechanism is further designed to dynamically fuse these sentiment features with user description, tweet content, numerical attributes, and categorical features. Finally, a Relational Graph Convolutional Network (RGCN) is employed to model heterogeneous social topology for robust bot detection. Experimental results on the TwiBot-20 benchmark dataset demonstrate that our method achieves a superior accuracy of 87.46%, significantly outperforming baseline models and validating the effectiveness of emoji-driven semantic and sentiment enhancement strategies.
Keywords: social bot detection; emoji; sentiment analysis; deep learning; RGCN social bot detection; emoji; sentiment analysis; deep learning; RGCN

Share and Cite

MDPI and ACS Style

Zeng, K.; Li, Z.; Wang, X. Emoji-Driven Sentiment Analysis for Social Bot Detection with Relational Graph Convolutional Networks. Sensors 2025, 25, 4179. https://doi.org/10.3390/s25134179

AMA Style

Zeng K, Li Z, Wang X. Emoji-Driven Sentiment Analysis for Social Bot Detection with Relational Graph Convolutional Networks. Sensors. 2025; 25(13):4179. https://doi.org/10.3390/s25134179

Chicago/Turabian Style

Zeng, Kaqian, Zhao Li, and Xiujuan Wang. 2025. "Emoji-Driven Sentiment Analysis for Social Bot Detection with Relational Graph Convolutional Networks" Sensors 25, no. 13: 4179. https://doi.org/10.3390/s25134179

APA Style

Zeng, K., Li, Z., & Wang, X. (2025). Emoji-Driven Sentiment Analysis for Social Bot Detection with Relational Graph Convolutional Networks. Sensors, 25(13), 4179. https://doi.org/10.3390/s25134179

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop