Automatic identification of personal insults on social news sites

Sara Owsley Sood*, Elizabeth F. Churchill, Judd Antin

*Corresponding author for this work

Research output: Contribution to journalArticle

53 Citations (Scopus)

Abstract

As online communities grow and the volume of user-generated content increases, the need for community management also rises. Community management has three main purposes: to create a positive experience for existing participants, to promote appropriate, socionormative behaviors, and to encourage potential participants to make contributions. Research indicates that the quality of content a potential participant sees on a site is highly influential; off-topic, negative comments with malicious intent are a particularly strong boundary to participation or set the tone for encouraging similar contributions. A problem for community managers, therefore, is the detection and elimination of such undesirable content. As a community grows, this undertaking becomes more daunting. Can an automated system aid community managers in this task? In this paper, we address this question through a machine learning approach to automatic detection of inappropriate negative user contributions. Our training corpus is a set of comments from a news commenting site that we tasked Amazon Mechanical Turk workers with labeling. Each comment is labeled for the presence of profanity, insults, and the object of the insults. Support vector machines trained on these data are combined with relevance and valence analysis systems in a multistep approach to the detection of inappropriate negative user contributions. The system shows great potential for semiautomated community management.

Original languageEnglish (US)
Pages (from-to)270-285
Number of pages16
JournalJournal of the American Society for Information Science and Technology
Volume63
Issue number2
DOIs
StatePublished - Feb 1 2012

Fingerprint

news
Managers
community
Labeling
Support vector machines
Learning systems
management
manager
Turk
internet community
systems analysis
News
worker
participation
learning
experience
Systems analysis
Participation
Machine learning
Support vector machine

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Human-Computer Interaction
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

@article{d5199f9eff114479a3509aedcb39a762,
title = "Automatic identification of personal insults on social news sites",
abstract = "As online communities grow and the volume of user-generated content increases, the need for community management also rises. Community management has three main purposes: to create a positive experience for existing participants, to promote appropriate, socionormative behaviors, and to encourage potential participants to make contributions. Research indicates that the quality of content a potential participant sees on a site is highly influential; off-topic, negative comments with malicious intent are a particularly strong boundary to participation or set the tone for encouraging similar contributions. A problem for community managers, therefore, is the detection and elimination of such undesirable content. As a community grows, this undertaking becomes more daunting. Can an automated system aid community managers in this task? In this paper, we address this question through a machine learning approach to automatic detection of inappropriate negative user contributions. Our training corpus is a set of comments from a news commenting site that we tasked Amazon Mechanical Turk workers with labeling. Each comment is labeled for the presence of profanity, insults, and the object of the insults. Support vector machines trained on these data are combined with relevance and valence analysis systems in a multistep approach to the detection of inappropriate negative user contributions. The system shows great potential for semiautomated community management.",
author = "Sood, {Sara Owsley} and Churchill, {Elizabeth F.} and Judd Antin",
year = "2012",
month = "2",
day = "1",
doi = "10.1002/asi.21690",
language = "English (US)",
volume = "63",
pages = "270--285",
journal = "Journal of the Association for Information Science and Technology",
issn = "2330-1635",
publisher = "John Wiley and Sons Ltd",
number = "2",

}

Automatic identification of personal insults on social news sites. / Sood, Sara Owsley; Churchill, Elizabeth F.; Antin, Judd.

In: Journal of the American Society for Information Science and Technology, Vol. 63, No. 2, 01.02.2012, p. 270-285.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic identification of personal insults on social news sites

AU - Sood, Sara Owsley

AU - Churchill, Elizabeth F.

AU - Antin, Judd

PY - 2012/2/1

Y1 - 2012/2/1

N2 - As online communities grow and the volume of user-generated content increases, the need for community management also rises. Community management has three main purposes: to create a positive experience for existing participants, to promote appropriate, socionormative behaviors, and to encourage potential participants to make contributions. Research indicates that the quality of content a potential participant sees on a site is highly influential; off-topic, negative comments with malicious intent are a particularly strong boundary to participation or set the tone for encouraging similar contributions. A problem for community managers, therefore, is the detection and elimination of such undesirable content. As a community grows, this undertaking becomes more daunting. Can an automated system aid community managers in this task? In this paper, we address this question through a machine learning approach to automatic detection of inappropriate negative user contributions. Our training corpus is a set of comments from a news commenting site that we tasked Amazon Mechanical Turk workers with labeling. Each comment is labeled for the presence of profanity, insults, and the object of the insults. Support vector machines trained on these data are combined with relevance and valence analysis systems in a multistep approach to the detection of inappropriate negative user contributions. The system shows great potential for semiautomated community management.

AB - As online communities grow and the volume of user-generated content increases, the need for community management also rises. Community management has three main purposes: to create a positive experience for existing participants, to promote appropriate, socionormative behaviors, and to encourage potential participants to make contributions. Research indicates that the quality of content a potential participant sees on a site is highly influential; off-topic, negative comments with malicious intent are a particularly strong boundary to participation or set the tone for encouraging similar contributions. A problem for community managers, therefore, is the detection and elimination of such undesirable content. As a community grows, this undertaking becomes more daunting. Can an automated system aid community managers in this task? In this paper, we address this question through a machine learning approach to automatic detection of inappropriate negative user contributions. Our training corpus is a set of comments from a news commenting site that we tasked Amazon Mechanical Turk workers with labeling. Each comment is labeled for the presence of profanity, insults, and the object of the insults. Support vector machines trained on these data are combined with relevance and valence analysis systems in a multistep approach to the detection of inappropriate negative user contributions. The system shows great potential for semiautomated community management.

UR - http://www.scopus.com/inward/record.url?scp=84857361560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857361560&partnerID=8YFLogxK

U2 - 10.1002/asi.21690

DO - 10.1002/asi.21690

M3 - Article

VL - 63

SP - 270

EP - 285

JO - Journal of the Association for Information Science and Technology

JF - Journal of the Association for Information Science and Technology

SN - 2330-1635

IS - 2

ER -