Advances in Social Bots

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Systems & Control Engineering".

Deadline for manuscript submissions: 15 February 2025 | Viewed by 590

Special Issue Editors


E-Mail Website
Guest Editor
Key Laboratory of Cyberculture Content Cognition and Detection, Ministry of Culture and Tourism, University of Science and Technology of China, Hefei 230026, China
Interests: social bots; cyber security; social networks
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Chinese Institute of Command and Control, Beijing 100089, China
Interests: artificial general intelligence; social network mining; knowledge graph

E-Mail Website
Guest Editor
Shenzhen Graduate School, Peking University, Shenzhen 518055, China
Interests: data science; cyber science; social networks

Special Issue Information

Dear Colleagues,

With the profound integration of technology and media, the ongoing development of social bots showcases an enhanced ability to mimic and engage in more covert machine behaviors. This new generation of social bots provides unprecedented convenience for public communication. However, the rapid development also presents substantial real-world risks in diverse domains. In the context of maintaining social stability, these automated systems have the potential to act as catalysts for social unrest, contributing to the proliferation of destabilizing elements. In the field of news dissemination, social bots may be employed to propagate misinformation or fake news, or they might filter and promote news stories based on specific algorithms and datasets, potentially leading to selection bias in the information presented. Moreover, they can be utilized to fabricate or amplify focus on particular issues, thereby manipulating public opinion. Regarding the aspect of financial security, the actions of social bots have the potential to contribute to a notable increase in instances of financial fraud, thereby posing a substantial threat to economic systems. In the realm of commercial marketing, there exists a potential for social bots to disseminate deceptive or exaggerated promotional content, undermining consumer interests and the equity of the marketplace. Crucially, the utilization of social bots gives rise to concerns regarding potential violations of personal privacy, thereby eliciting widespread apprehension. Behind this challenge lies a multitude of research topics spanning various disciplines, including bot detection, emotion analysis, stance detection, human–machine conversation, intelligent interaction, and content generation. Addressing these research topics is essential to guide the advancement of social bot technology. This will ensure that its development promotes communication convenience while minimizing any potential negative effects on societal, communication, financial, marketing, and personal domains.

This Special Issue solicits papers on new research achievements and challenges in social bots.

Topics of interest in this Special Issue include but are not limited to the following:

  • Social Bot Detection in Social Networks;
  • Emotion Analysis in Social Bots;
  • Stance Detection in Social Bots;
  • Human–Machine Conversation;
  • Artificial Intelligence for Social Bots;
  • Intelligent Interaction in Social Bots;
  • Multi-Modal Content Generation;
  • Computational Modelling of Information Diffusion;
  • Misinformation Detection in Social Media;
  • Social Bot Influence Analysis;
  • Dynamics of Online Opinion Propaganda.

Dr. Yangyang Li
Dr. Yangzhao Yang
Dr. Hu Huang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • social agent
  • multi-agent
  • conversational AI
  • emotion detection
  • sentiment analysis
  • social interaction modelling
  • social bot detection
  • multi-modal content generation
  • user experience evaluation

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

16 pages, 1486 KiB  
Article
Research on Aspect-Level Sentiment Analysis Based on Adversarial Training and Dependency Parsing
by Erfeng Xu, Junwu Zhu, Luchen Zhang, Yi Wang and Wei Lin
Electronics 2024, 13(10), 1993; https://doi.org/10.3390/electronics13101993 - 20 May 2024
Viewed by 124
Abstract
Aspect-level sentiment analysis is used to predict the sentiment polarity of a specific aspect in a sentence. However, most current research cannot fully utilize semantic information, and the models lack robustness. Therefore, this article proposes a model for aspect-level sentiment analysis based on [...] Read more.
Aspect-level sentiment analysis is used to predict the sentiment polarity of a specific aspect in a sentence. However, most current research cannot fully utilize semantic information, and the models lack robustness. Therefore, this article proposes a model for aspect-level sentiment analysis based on a combination of adversarial training and dependency syntax analysis. First, BERT is used to transform word vectors and construct adjacency matrices with dependency syntactic relationships to better extract semantic dependency relationships and features between sentence components. A multi-head attention mechanism is used to fuse the features of the two parts, simultaneously perform adversarial training on the BERT embedding layer to enhance model robustness, and, finally, to predict emotional polarity. The model was tested on the SemEval 2014 Task 4 dataset. The experimental results showed that, compared with the baseline model, the model achieved significant performance improvement after incorporating adversarial training and dependency syntax relationships. Full article
(This article belongs to the Special Issue Advances in Social Bots)
Show Figures

Figure 1

Back to TopTop