Abstract

Social network and publishing platforms, such as Twitter, support the concept of a secret proprietary verification process, for han- dles they deem worthy of platform-wide public interest. In line with significant prior work which suggests that possessing such a status symbolizes enhanced credibility in the eyes of the platform audience, a verified badge is clearly coveted among public figures and brands. What are less obvious are the inner workings of the verification process and what being verified represents. This lack of clarity, coupled with the flak that Twitter received by extend- ing aforementioned status to political extremists in 2017, backed Twitter into publicly admitting that the process and what the status represented needed to be rethought. With this in mind, we seek to unravel the aspects of a user’s profile which likely engender or preclude verification. The aim of the paper is two-fold: First, we test if discerning the verification status of a handle from profile metadata and content features is feasible. Second, we unravel the features which have the greatest bearing on a handle’s verification status. We collected a dataset con- sisting of profile metadata of all 231,235 verified English-speaking users (as of July 2018), a control sample of 175,930 non-verified English-speaking users and all their 494 million tweets over a one year collection period. Our proposed models are able to reliably identify verification status (Area under curve AUC > 99%). We show that number of public list memberships, presence of neutral sen- timent in tweets and an authoritative language style are the most pertinent predictors of verification status. To the best of our knowledge, this work represents the first attempt at discerning and classifying verification worthy users on

Abstract

Social dynamics are based on human needs for trust, support, resource sharing, irrespective of whether they operate in real life or in a virtual setting. Massively multiplayer online role-playing games (MMORPGS) serve as enablers of leisurely social activity and are important tools for social interactions. Past research has shown that socially dense gaming environments like MMORPGs can be used to study important social phenomena, which may operate in real life, too. We describe the process of social exploration to entail the following components 1) finding the balance between personal and social time 2) making choice between a large number of weak ties or few strong social ties. 3) finding a social group. In general, these are the major determinants of an individual’s social life. This paper looks into the phenomenon of social exploration in an activity based online social environment. We study this process through the lens of the following research questions, 1) What are the different social behavior types? 2) Is there a change in a player’s social behavior over time? 3) Are certain social behaviors more stable than the others? 4) Can longitudinal research of player behavior help shed light on the social dynamics and processes in the network? We use an unsupervised machine learning approach to come up with 4 different social behavior types - Lone Wolf, Pack Wolf of Small Pack, Pack Wolf of a Large Pack and Social Butterfly. The types represent the degree of socialization of players in the game. Our research reveals that social behaviors change with time. While lone wolf and pack wolf of small pack are more stable social behaviors, pack wolf of large pack and social butterflies are more transient. We also observe that players progressively move from large groups with weak social ties to settle in small groups with stronger ties. Index Terms—Social Exploration, Social Behavior Typology, MMORPG, Clusterin

Abstract

Massively Multiplayer Online Role-Playing Games (MMORPGs) are persistent virtual environments where millions of players interact in an online manner. We study the problem of player churn and social contagion using MMORPG game logs by analyzing the impact of a node’s churn behavior on its immediate neighborhood or group. The two key research questions in this paper are - When an active node, ego, becomes dormant, what is the impact on the activity behavior of ego’s immediate neighbor, alter, 1) based on ego’s characteristics and ego’s relationship with alter and 2) based on the activity behavior of alter’s remaining neighbors. We use a supervised learning framework to study the impact of player churn and social contagion. Experimental results show that the classification models perform substantially better than random for both the research problems. Finally, we use a data-driven approach to propose a player typology based on degree of socialization and analyze churn behavior among these player types. Experimental results show that the loner player type is much more likely to churn than the socializer player types and as the degree of socialization decreases among socializers, the propensity to churn increases. Index Terms—churn, social contagion, supervised learning, clustering, player typology

Abstract

Livestreaming platforms enable content producers, or streamers, to broadcast creative content to a potentially large viewer base. Chatrooms form an integral part of such platforms, enabling viewers to interact both with the streamer, and amongst themselves. Streams with high engagement (many viewers and active chatters) are typically considered engaging, and often promoted to end users by means of recommendation algorithms, and exposed to better monetization opportunities via revenue share from platform advertising, viewer donations, and third- party sponsorships. Given such incentives, some streamers make use of fraudulent means to increase perceived engagement by simulating chatter via fake “chatbots” which can be purchased from shady online marketplaces. This inauthentic engagement can negatively influence recommendation, hurt streamer and viewer trust in the platform, and harm monetization for hon- est streamers. In this paper, we tackle the novel problem of automating detection of chatbots on livestreaming platforms. To this end, we first formalize the livestreaming chatbot detection problem and characterize differences between botted and gen- uine chatter behavior observed from a real-world livestream- ing chatter dataset collected from Twitch.tv. We then propose S HERLOCK , which posits a two-stage approach of detecting chatbotted streams, and subsequently detecting the constituent chatbots. Finally, we demonstrate effectiveness on both real and synthetic data: to this end, we propose a novel strategy for collecting labeled, synthetic chatter dataset (typically unavailable) from such platforms, enabling evaluation of proposed detection approaches against chatbot behaviors with varying signatures. Our approach achieves .97 precision/recall on the real-world dataset, and .80+ F1 scores across most simulated attack settings.

Abstract

Road safety mapping using satellite images is a cost-effective but a challenging problem for smart city planning. The scarcity of labeled data, misalignment and ambiguity makes it hard to learn efficient embeddings in order to classify between safe and dangerous road segments. In this paper, we address the challenges using a region guided attention network. In our model, we extract global features from a base network and augment it with local features obtained using the region guided attention network. In addition, we perform domain adaptation for unlabeled target data. In order to bridge the gap between safe samples and dangerous samples from source and target respectively, we propose a loss function based on within and between class covariance matrices. We conduct experiments on a public dataset of London to show that the algorithm achieves significant results with the classification accuracy of 86.21%. We obtain an increase of 4% accuracy for NYC using domain adaptation network.

Abstract

In recent years, there has been an explosion in the number of memesbeing created and circulated in online social networks. Despite theirrapidly increasing impact on how we communicate online, memeimages are virtually inaccessible to the visually impaired users. Ex-isting automated assistive systems that were primarily devised fornatural photos in social media, overlook the specific fine-grainedvisual details in meme images. In this paper, we concentrate ondescribing one such prominent visual detail: the meme face emo-tion. We propose a novel automated method that enables visuallyimpaired social media users to understand and appreciate memeface emotions with the help of rich textual captions. We first collecta challenging dataset of meme face emotion captions to supportfuture research in face emotion understanding. We design a two-stage approach that significantly outperforms baseline approaches across all the standard captioning metrics and also generates richerdiscriminative captions. By validating our solution with the helpof visually impaired social media users, we show that our emotioncaptions enable them to understand and appreciate one of the mostpopular classes of meme images encountered on the Internet forthe first time. Code, data, and models are publicly available.

Abstract

Identifying medical persona from a social media post is critical for drug marketing, pharmacovigilance and patient recruitment. Medical persona classification aims to computationally model the medical persona associated with a social media post. We present a novel deep learning model for this task which consists of two parts: Convolutional Neural Networks (CNNs), which extract highly relevant features from the sentences of a social media post and average pooling, which aggregates the sentence embeddings to obtain task-specific document embedding. We compare our approach against standard baselines, such as Term Frequency - Inverse Document Frequency (TF-IDF), averaged word embedding based methods and popular neural architectures, such as CNN-Long Short Term Memory (CNN-LSTM) and Hierarchical Attention Networks (HANs). Our model achieves an improvement of 19.7% for classification accuracy and 20.1% for micro F1 measure over the current state-of-the-art. We eliminate the need for manual labeling by employing a distant supervision based method to obtain labeled examples for training the models. We thoroughly analyze our model to discover cues that are indicative of a particular persona. Particularly, we use first derivative saliency to identify the salient words in a particular social media post.

Abstract

Identifying medical persona from a social media post is of paramount importance for drug marketing and pharmacovigilance. In this work, we propose multiple approaches to infer the medical persona associated with a social media post. We pose this as a supervised multi-label text classification problem. The main challenge is to identify the hidden cues in a post that are indicative of a particular persona. We first propose a large set of manually engineered features for this task. Further, we propose multiple neural network based architectures to extract useful features from these posts using pre-trained word embeddings. Our experiments on thousands of blogs and tweets show that the proposed approach results in 7% and 5% gain in F-measure over manual feature engineering based approach for blogs and tweets respectively.

Abstract

Recognition based graphical passwords are inherently vulnerable to shoulder surfing attacks because of their visual mode of interaction. In this paper, we propose and evaluate two novel shoulder-surfing defense techniques for recognition based graphical passwords. These techniques are based on WYSWYE (Where You See is What You Enter) strategy, where the user identifies a pattern of password images within a presented grid of images and replicates it onto another grid. We conducted controlled laboratory experiments to evaluate the usability and security of the proposed techniques. Both the schemes had high login success rates with no failures in authentication. More than seventy percent of participants successfully logged on to the system in their first attempt in both the schemes. The participants were satisfied with the schemes and were willing to use it in public places. In addition, both the schemes were significantly secure against shoulder surfing than normal unprotected recognition based graphical passwords. The login efficiency improved with practice in one of the proposed scheme. We believe, WYSWYE strategy has considerable potential and can easily be extended to other types of authentication systems such as text passwords and PINS.

Abstract

In this paper we propose and evaluate Marasim, a novel Jigsaw based graphical authentication mechanism using tagging. Marasim is aimed at achieving the security of random images with the memorability of personal images. Our scheme relies on the human ability to remember a personal image and later recognize the alternate visual representations (images) of the concepts occurred in the image. These concepts are retrieved from the tags assigned to the image. We illustrate how a Jigsaw based approach helps to create a portfolio of system-chosen random images to be used for authentication. The paper describes the complete design of Marasim along with the empirical studies of Marasim that provide evidences of increased memorability. Results show that 93% of all participants succeeded in the authentication tests using Marasim after three months while 71% succeeded in authentication tests using Marasim after nine months. Our findings indicate that Marasim has potential applications, especially where text input is hard (e.g., PDAs or ATMs), or in situations where passwords are infrequently used (e.g., web site passwords).