Homa Hosseinmardi

Towards understanding cyberbullying behavior in a semi-anonymous social network

Cyberbullying has emerged as an important and growing social problem, wherein people use online social networks and mobile phones to bully victims with offensive text, images, audio and video on a 24/7 basis. This paper studies negative user behavior in the Ask.fm social network, a popular new site that has led to many cases of cyberbullying, some leading to suicidal behavior.We examine the occurrence of negative words in Ask.fms question+answer profiles along with the social network of “likes” of questions+answers. We also examine properties of users with “cutting” behavior in this social network.

Analyzing Labeled Cyberbullying Incidents on the Instagram Social Network

Cyberbullying is a growing problem affecting more than half of all American teens. The main goal of this paper is to study labeled cyberbullying incidents in the Instagram social network. In this work, we have collected a sample data set consisting of Instagram images and their associated comments. We then designed a labeling study and employed human contributors at the crowd-sourced CrowdFlower website to label these media sessions for cyberbullying. A detailed analysis of the labeled data is then presented, including a study of relationships between cyberbullying and a host of features such as cyberaggression, profanity, social graph features, temporal commenting behavior, linguistic content, and image content.

Careful what you share in six seconds: Detecting cyberbullying instances in Vine

As online social networks have grown in popularity, teenage users have become increasingly exposed to the threats of cyberbullying. The primary goal of this research paper is to investigate cyberbullying behaviors in Vine, a mobile based video-sharing online social network, and design novel approaches to automatically detect instances of cyberbullying over Vine media sessions. We first collect a set of Vine video sessions and use CrowdFlower, a crowd-sourced website, to label the media sessions for cyberbullying and cyberaggression. We then perform a detailed analysis of cyberbullying behavior in Vine. Based on the labeled data, we design a classifier to detect instances of cyberbullying and evaluate the performance of that classifier.

Prediction of cyberbullying incidents in a media-based social network

Cyberbullying is a major problem affecting more than half of all American teens. Prior work has largely focused on detecting cyberbullying after the fact. In this paper, we investigate the prediction of cyberbullying incidents in Instagram, a popular media-based social network. The novelty of this work is building a predictor that can anticipate the occurrence of cyberbullying incidents before they happen. The Instagram media-based social network is well-suited to such prediction since there is an initial posting of an image typically with an associated text caption, followed later by the text comments that form the basis of a specific cyberbullying incident. We extract several important features from the initial posting data for automated cyberbullying prediction, including profanity and linguistic content of the text caption, image content, as well as social graph parameters and temporal content behavior. Evaluations using a real-world Instagram dataset demonstrate that our method achieves high performance in predicting the occurrence of cyberbullying incidents.

Establishing Multi-cast Groups in Computational Robotic Materials

We study an efficient ad hoc multicast communication protocol for next-generation large-scale distributed cyber-physical systems that we dub Computational Robotic Materials (CRMs). CRMs tightly integrate sensing, actuation, computation and communication, and can enable materials that can change their shape, appearance and function in response to local sensing and distributed information processing. As CRMs potentially consist of thousands of nodes with limited processing power and memory, communication in such systems poses serious challenges. For example, when processing a gesture recorded by the CRM, only a subset of nodes involved in its detection should communicate amongst themselves for distributed proessing. In previous work, we proposed a Bloom filter-based approach to label the multicast group with an approximate error-resilient multicast tag that captures the temporal and spatial characteristics of the sensor group. A Bloom filter is a space-efficient probabilistic data structure that is used to test whether an element is a member of a set. We describe our Bloom filter-based multicast communication (BMC) protocol, and report experimental results using a 48-node Computational Robotic Material test-bed engaged in shape and gesture recognition.

Distributed Spatiotemporal Gesture Recognition in Sensor Arrays

We present algorithms for gesture recognition using in-network processing in distributed sensor arrays embedded within systems such as tactile input devices, sensing skins for robotic applications, and smart walls. We describe three distributed gesture-recognition algorithms that are designed to function on sensor arrays with minimal computational power, limited memory, limited bandwidth, and possibly unreliable communication. These constraints cause storage of gesture templates within the system and distributed consensus algorithms for recognizing gestures to be difficult. Building up on a chain vector encoding algorithm commonly used for gesture recognition on a central computer, we approach this problem by dividing the gesture dataset between nodes such that each node has access to the complete dataset via its neighbors. Nodes share gesture information among each other, then each node tries to identify the gesture. In order to distribute the computational load among all nodes, we also investigate an alternative algorithm, in which each node that detects a motion will apply a recognition algorithm to part of the input gesture, then share its data with all other motion nodes. Next, we show that a hybrid algorithm that distributes both computation and template storage can address trade-offs between memory and computational efficiency.

Bloom Filter-Based Ad Hoc Multicast Communication in Cyber-Physical Systems and Computational Materials

This article presents an efficient ad hoc multicast communication protocol for next-generation cyber-physical systems and computational materials. Communication with such systems would be gestural, and when cells within such materials detect a motion, they would share that information with each other. We want to achieve efficient communication among only the group of nodes that sense a particular (gestural) event. Our approach is to employ a Bloom filter-based approach to label the multicast group with an approximate error-resilient multicast tag that captures the temporal and spatial characteristics of the sensor group. A Bloom filter is a space-efficient probabilistic data structure that is used to test whether an element is a member of a set. We describe our Bloom filter-based multicast communication (BMC) protocol, and report simulation results.

Analysis and detection of labeled cyberbullying instances in Vine, a video-based social network

The last decade has experienced an exponential growth of popularity in online social networks. This growth in popularity has also paved the way for the threat of cyberbullying to grow to an extent that was never seen before. Online social network users are now constantly under the threat of cyberbullying from predators and stalkers. In our research paper, we perform a thorough investigation of cyberbullying instances in Vine, a video-based online social network. We collect a set of media sessions (shared videos with their associated meta-data) and then label those using CrowdFlower, a crowd-sourced website for cyberaggression and cyberbullying. We also perform a second survey that labels the videos’ contents and emotions exhibited. After the labeling of the media sessions, we provide a detailed analysis of the media sessions to investigate the cyberbullying and cyberaggression behavior in Vine. After the analysis, we train different classifiers based upon the labeled media sessions. We then investigate, evaluate and compare the classifers’ performances to detect instances of cyberbullying.

Poster: Detection of Cyberbullying in a Mobile Social Network: Systems Issues

Cyberbullying is a major problem affecting more than half of all American teens, and has been attributed to suicidal behavior among teens. Instagram, a media-based mobile social network, is one of the most popular social networks used for cyberbullying. In this paper, we describe the development of classifiers to detect cyberbullying in Instagram. We identify systems issues that need to be considered in the design of a cyberbullying detection system.

Scalable and timely detection of cyberbullying in online social networks

Cyberbullying in Online Social Networks (OSNs) has grown to be a serious problem among teenagers. While a considerable amount of research has been conducted focusing on designing highly accurate classifiers to automatically detect cyberbullying instances in OSNs, two key practical issues remain to be worked upon, namely scalability of a cyberbullying detection system and timeliness of raising alerts whenever cyberbullying occurs. These two issues form the motivation of our work. We propose a multi-stage cyberbullying detection solution that drastically reduces the classification time and the time to raise alerts. The proposed system is highly scalable without sacrificing accuracy and highly responsive in raising alerts. The design is comprised of two novel components, a dynamic priority scheduler and an incremental classification mechanism. We have implemented this solution, and using data obtained from Vine, we conducted a thorough performance evaluation to demonstrate the utility and scalability of each of these components. We show that our complete solution is significantly more scalable and responsive than the current state of the art.