View in EDS

When comments aren't what they seem: The social media comment toxicity detector for understanding contextual comments.

Saved in:
Bibliographic Details
Title: When comments aren't what they seem: The social media comment toxicity detector for understanding contextual comments.
Authors: Song, Zichen1 (AUTHOR) songzch21@lzu.edu.cn, Fan, Xiaopeng1 (AUTHOR) fanxp2023@lzu.edu.cn, Wang, Yutong1 (AUTHOR) yutongwang2023@lzu.edu.cn, Yan, Feixuan1 (AUTHOR) yanfx2023@lzu.edu.cn, Wu, Zijin1 (AUTHOR) wuzj2023@lzu.edu.cn, Kang, Zhongfeng1 (AUTHOR) kangzf@lzu.edu.cn
Source: Expert Systems with Applications. Apr2026, Vol. 305, pN.PAG-N.PAG. 1p.
Subjects: Context-aware computing, Generative pre-trained transformers, Machine learning, Sentiment analysis, Electronic data processing
Abstract: Social media comments often contain toxic, sarcastic, or ambiguous language, challenging traditional toxicity detection models. However, most existing methods treat comments as isolated units and rely solely on surface-level textual cues, making them ineffective in identifying implicit toxicity such as sarcasm or context-dependent insults. These limitations hinder their performance in real-world scenarios, where toxicity often emerges across multi-turn interactions. This paper proposes a context-aware interactive framework using GPT models to simulate human-like interactions, transforming single comments into multi-level threads. This approach improves toxicity detection by leveraging contextual dialogue. We evaluate our method on 5018 comments from platforms such as Zhihu, Bilibili, Weibo, YouTube, and RedNote. Our experiments show that our method outperforms traditional models, especially on YouTube, where sensitive word frequency is high. Additionally, our approach demonstrates strong multilingual support, successfully detecting toxicity in six languages. This paper also compares the performance of GPT-4O, GPT-4, GPT-3.5 and DeepSeek-V3, highlighting the advantage of multimodal processing in the former for more robust detection. The dataset we have collected is publicly available at https://github.com/kanglzu/When-Comments-Aren-t-What-They-Seem. [ABSTRACT FROM AUTHOR]
Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 191526000
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: When comments aren't what they seem: The social media comment toxicity detector for understanding contextual comments.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Song%2C+Zichen%22">Song, Zichen</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> songzch21@lzu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Fan%2C+Xiaopeng%22">Fan, Xiaopeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> fanxp2023@lzu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Yutong%22">Wang, Yutong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yutongwang2023@lzu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Yan%2C+Feixuan%22">Yan, Feixuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yanfx2023@lzu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Zijin%22">Wu, Zijin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wuzj2023@lzu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Kang%2C+Zhongfeng%22">Kang, Zhongfeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> kangzf@lzu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Expert+Systems+with+Applications%22">Expert Systems with Applications</searchLink>. Apr2026, Vol. 305, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Context-aware+computing%22">Context-aware computing</searchLink><br /><searchLink fieldCode="DE" term="%22Generative+pre-trained+transformers%22">Generative pre-trained transformers</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Sentiment+analysis%22">Sentiment analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Electronic+data+processing%22">Electronic data processing</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Social media comments often contain toxic, sarcastic, or ambiguous language, challenging traditional toxicity detection models. However, most existing methods treat comments as isolated units and rely solely on surface-level textual cues, making them ineffective in identifying implicit toxicity such as sarcasm or context-dependent insults. These limitations hinder their performance in real-world scenarios, where toxicity often emerges across multi-turn interactions. This paper proposes a context-aware interactive framework using GPT models to simulate human-like interactions, transforming single comments into multi-level threads. This approach improves toxicity detection by leveraging contextual dialogue. We evaluate our method on 5018 comments from platforms such as Zhihu, Bilibili, Weibo, YouTube, and RedNote. Our experiments show that our method outperforms traditional models, especially on YouTube, where sensitive word frequency is high. Additionally, our approach demonstrates strong multilingual support, successfully detecting toxicity in six languages. This paper also compares the performance of GPT-4O, GPT-4, GPT-3.5 and DeepSeek-V3, highlighting the advantage of multimodal processing in the former for more robust detection. The dataset we have collected is publicly available at https://github.com/kanglzu/When-Comments-Aren-t-What-They-Seem. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=191526000
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.eswa.2025.130902
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Context-aware computing
        Type: general
      – SubjectFull: Generative pre-trained transformers
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Sentiment analysis
        Type: general
      – SubjectFull: Electronic data processing
        Type: general
    Titles:
      – TitleFull: When comments aren't what they seem: The social media comment toxicity detector for understanding contextual comments.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Song, Zichen
      – PersonEntity:
          Name:
            NameFull: Fan, Xiaopeng
      – PersonEntity:
          Name:
            NameFull: Wang, Yutong
      – PersonEntity:
          Name:
            NameFull: Yan, Feixuan
      – PersonEntity:
          Name:
            NameFull: Wu, Zijin
      – PersonEntity:
          Name:
            NameFull: Kang, Zhongfeng
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 05
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 09574174
          Numbering:
            – Type: volume
              Value: 305
          Titles:
            – TitleFull: Expert Systems with Applications
              Type: main
ResultId 1