Cyberbullying has become one of the most pressing online risks for adolescents and has raised serious concerns in society. Recent years have witnessed a surge in research aimed at developing principled learning models to detect cyberbullying behaviors. These efforts have primarily focused on building a single generic classification model to differentiate bullying content from normal (non-bullying) content among all users. These models treat users equally and overlook idiosyncratic information about users that might facilitate the accurate detection of cyberbullying. In this paper, we propose a personalized cyberbullying detection framework, PI-Bully, that draws on empirical findings from psychology highlighting unique characteristics of victims and bullies and peer influence from like-minded users as predictors of cyberbullying behaviors. Our framework is novel in its ability to model peer influence in a collaborative environment and tailor cyberbullying prediction for each individual user. Extensive experimental evaluations on real-world datasets corroborate the effectiveness of the proposed framework.
more »
« less
Personalized Learning for Cyberbullying Detection
Cyberbullying has become one of the most pressing online risks for adolescents and has raised serious concerns in society. Traditional efforts are primarily devoted to building a single generic classification model for all users to differentiate bullying behaviors from the normal content [6, 3, 1, 2, 4]. Despite its empirical success, these models treat users equally and inevitably ignore the idiosyncrasies of users. Recent studies from psychology and sociology suggest that the occurrence of cyberbullying has a strong connection with the personality of victims and bullies embedded in the user-generated content, and the peer influence from like-minded users. In this paper, we propose a personalized cyberbullying detection framework PI-Bully with peer influence in a collaborative environment to tailor the prediction for each individual. In particular, the personalized classifier of each individual consists of three components: a global model that captures the commonality shared by all users, a personalized model that expresses the idiosyncratic personality of each specific user, and a third component that encodes the peer influence received from like-minded users. Most of the existing methods adopt a two-stage approach: they first apply feature engineering to capture the cyberbullying patterns and then employ machine learning classifiers to detect cyberbullying behaviors. However, building a personalized cyberbullying detection framework that is customized to each individual remains a challenging task, in large part because: (1) Social media data is often sparse, noisy and high-dimensional (2) It is important to capture the commonality shared by all users as well as idiosyncratic aspects of the personality of each individual for automatic cyberbullying detection; (3) In reality, a potential victim of cyberbullying is often influenced by peers and the influences from different users could be quite diverse. Hence, it is imperative to develop a way to encode the diversity of peer influence for cyberbullying detection. To summarize, we study a novel problem of personalized cyberbullying detection with peer influence in a collaborative environment, which is able to jointly model users' common features, unique personalities and peer influence to identify cyberbullying cases.
more »
« less
- Award ID(s):
- 1719722
- PAR ID:
- 10067396
- Date Published:
- Journal Name:
- Doctoral Consortium of the International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Collaborative systems design is a human-centered activity dependent on individual decision-making processes. Personality traits have been found to influence individual behaviors and tendencies to compete or cooperate. This paper investigates the effects of Big Five and Locus of Control personality traits on negotiated outcomes of a simplified collaborative engineering design task. Secondary data includes results from short-form personality inventories and outcomes of pair design tasks. The data includes ten sessions of four participants each, where each participant completes a sequence of 12 pair tasks involving design space exploration and negotiation. Regression analysis shows a statistically-significant relationship between Big Five and Locus of Control and total individual value accumulated across the 12 design tasks. Results show the Big Five, aggregating extraversion, agreeableness, conscientiousness, neuroticism, and intellect/imagination to a single factor, negatively affects individual value and internal Locus of Control positively affects individual value. Future work should consider a dedicated experiment to refine understanding of how personality traits influence collaborative systems design and propose interventions to improve collaborative design processes.more » « less
-
null (Ed.)Due to the prevalence and severe consequences of cyberbullying, numerous research works have focused on mining and analyzing social network data to understand cyberbullying behavior and then using the gathered insights to develop accurate classifiers to detect cyberbullying. Some recent works have been proposed to leverage the detection classifiers in a centralized cyberbullying detection system and send notifications to the concerned authority whenever a person is perceived to be victimized. However, two concerns limit the effectiveness of a centralized cyberbullying detection system. First, a centralized detection system gives a uniform severity level of alerts to everyone, even though individual guardians might have different tolerance levels when it comes to what constitutes cyberbullying. Second, the volume of data being generated by old and new social media makes it computationally prohibitive for a centralized cyberbullying detection system to be a viable solution. In this work, we propose BullyAlert, an android mobile application for guardians that allows the computations to be delegated to the hand-held devices. In addition to that, we incorporate an adaptive classification mechanism to accommodate the dynamic tolerance level of guardians when receiving cyberbullying alerts. Finally, we include a preliminary user analysis of guardians and monitored users using the data collected from BullyAlert usage.more » « less
-
Over the last decade, research has revealed the high prevalence of cyberbullying among youth and raised serious concerns in society. Information on the social media platforms where cyberbullying is most prevalent (e.g., Instagram, Facebook, Twitter) is inherently multi-modal, yet most existing work on cyberbullying identification has focused solely on building generic classification models that rely exclusively on text analysis of online social media sessions (e.g., posts). Despite their empirical success, these efforts ignore the multi-modal information manifested in social media data (e.g., image, video, user profile, time, and location), and thus fail to offer a comprehensive understanding of cyberbullying. Conventionally, when information from different modalities is presented together, it often reveals complementary insights about the application domain and facilitates better learning performance. In this paper, we study the novel problem of cyberbullying detection within a multi-modal context by exploiting social media data in a collaborative way. This task, however, is challenging due to the complex combination of both cross-modal correlations among various modalities and structural dependencies between different social media sessions, and the diverse attribute information of different modalities. To address these challenges, we propose XBully, a novel cyberbullying detection framework, that first reformulates multi-modal social media data as a heterogeneous network and then aims to learn node embedding representations upon it. Extensive experimental evaluations on real-world multi-modal social media datasets show that the XBully framework is superior to the state-of-the-art cyberbullying detection models.more » « less
-
Today, face editing is widely used to refine/alter photos in both professional and recreational settings. Yet it is also used to modify (and repost) existing online photos for cyberbullying. Our work considers an important open question: 'How can we support the collaborative use of face editing on social platforms while protecting against unacceptable edits and reposts by others?' This is challenging because, as our user study shows, users vary widely in their definition of what edits are (un)acceptable. Any global filter policy deployed by social platforms is unlikely to address the needs of all users, but hinders social interactions enabled by photo editing. Instead, we argue that face edit protection policies should be implemented by social platforms based on individual user preferences. When posting an original photo online, a user can choose to specify the types of face edits (dis)allowed on the photo. Social platforms use these per-photo edit policies to moderate future photo uploads, i.e., edited photos containing modifications that violate the original photo's policy are either blocked or shelved for user approval. Realizing this personalized protection, however, faces two immediate challenges: (1) how to accurately recognize specific modifications, if any, contained in a photo; and (2) how to associate an edited photo with its original photo (and thus the edit policy). We show that these challenges can be addressed by combining highly efficient hashing based image search and scalable semantic image comparison, and build a prototype protector (Alethia) covering nine edit types. Evaluations using IRB-approved user studies and data-driven experiments (on 839K face photos) show that Alethia accurately recognizes edited photos that violate user policies and induces a feeling of protection to study participants. This demonstrates the initial feasibility of personalized face edit protection. We also discuss current limitations and future directions to push the concept forward.more » « less