| NSF Org: |
CNS Division Of Computer and Network Systems |
| Recipient: |
|
| Initial Amendment Date: | May 28, 2020 |
| Latest Amendment Date: | May 28, 2020 |
| Award Number: | 2013801 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Sara Kiesler
skiesler@nsf.gov (703)292-8643 CNS Division Of Computer and Network Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | December 3, 2019 |
| End Date: | June 30, 2020 (Estimated) |
| Total Intended Award Amount: | $13,238.00 |
| Total Awarded Amount to Date: | $45,238.00 |
| Funds Obligated to Date: |
FY 2016 = $16,000.00 FY 2017 = $16,000.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1600 HAMPTON ST COLUMBIA SC US 29208-3403 (803)777-7093 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
SC US 29208-0001 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): |
Special Projects - CNS, Secure &Trustworthy Cyberspace |
| Primary Program Source: |
01001617DB NSF RESEARCH & RELATED ACTIVIT 01001718DB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
As social media permeates our daily life, there has been a sharp rise in the use of social media to humiliate, bully, and threaten others, which has come with harmful consequences such as emotional distress, depression, and suicide. The October 2014 Pew Research survey shows that 73% of adult Internet users have observed online harassment and 40% have experienced it. The prevalence and serious consequences of online harassment present both social and technological challenges. This project identifies harassing messages in social media, through a combination of text analysis and the use of other clues in the social media (e.g., indications of power relationships between sender and receiver of a potentially harassing message.) The project will develop prototypes to detect harassing messages in Twitter; the proposed techniques can be adapted to other platforms, such as Facebook, online forums, and blogs. An interdisciplinary team of computer scientists, social scientists, urban and public affairs professionals, educators, and the participation of college and high schools students in the research will ensure wide impact of scientific research on the support for safe social interactions.
This project combines social science theory and human judgment of potential harassment examples from social media, in both school and workplace contexts, to operationalize the detection of harassing messages and offenders. It develops comprehensive and reliable context-aware techniques (using machine learning, text mining, natural language processing, and social network analysis) to glean information about the people involved and their interconnected network of relationships, and to determine and evaluate potential harassment and harassers. The key innovations of this work include: (1) identification of the generic language of insult, characterized by profanities and other general patterns of verbal abuse, and recognition of target-dependent offensive language involving sensitive topics that are personal to a specific individual or social circle; (2) prediction of harassment-specific emotion evoked in a recipient after reading messages by leveraging conversation history as well as sender's emotions; (3) recognition of a sender's malicious intent behind messages based on the aspects of power, truth (approximated by trust), and familiarity; (4) a harmfulness assessment of harassing messages by fusing aforementioned language, emotion, and intent factors; and (5) detection of harassers from their aggregated behaviors, such as harassment frequency, duration, and coverage measures, for effective prevention and intervention.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Online harassment and toxic content have many negative impacts on human interaction and society as a whole. In extreme cases this leads individuals to depression and even suicide. Social media companies are trying to tackle this issue, and have reportedly hired thousands of human moderators to intercept and purge such content, so far with unsatisfactory results. Automated moderation is difficult due to the context sensitivity of human language, changes in the cultural acceptability of potentially harassing keywords, and relative sparsity of harassing content.
In this interdisciplinary work, we have studied online harassment by going beyond the key-word notations to identify the context of online harassment and toxicity. We employed several key concepts from social psychology such as conversation analysis, intentionality, and group phenomena to identify and analyze online harassment. We have developed and provided to the research community two unique datasets (a) a dataset covering different aspects of the problem (sexual, racial, appearance, intelligence, politics, generic), and (b) a tagged dataset of anonymized online content of adolescent conversations, capturing both context and their language preferences. Our own analyses of these datasets enriches the understanding of the harassment problem in at least two respects. First context matters in the assessment of harassing content, including prior relationships between the participants, community membership (and the insider-outsider phenomenon in particular), cohort linguistic practices and the presence of exonerating content (to distinguish threatening tweets from superficially harassing curse-word laden friendly banter). Second, harassment sparsity not only threatens the practicality of machine learning classifiers, but also the risk of false alarms given a high base rate of non-harassing content (i.e., sparsity of positive cases). Both properties of the harassment problem require a top-down knowledge-based approach to the detection of harassment in contrast to the more prevalent data driven efforts.
To overcome data sparsity in harassment we have examined detection issues in a related model domain of antisocial behavior: extremist communication. We show how knowledge bases for religion, ideology and hate support computational detection of extremists. This knowledge based approach successfully excludes likely mislabeled users and therefore addresses the false alarm problem. This knowledge based approach also enhances computational community detection, relevant to the identification of toxic user groups in online communities. The project provided extensive opportunity for training for students and postdocs from computer science as well as cognitive science in a highly inclusive, interdisciplinary setting.
Last Modified: 11/15/2020
Modified by: Amit Sheth
Please report errors in award information by writing to: awardsearch@nsf.gov.
