Anna Squicciarini

AAAI Conference 2022 System Paper

A Synthetic Prediction Market for Estimating Confidence in Published Work

• Sarah Rajtmajer
• Christopher Griffin
• Jian Wu
• Robert Fraleigh
• Laxmaan Balaji
• Anna Squicciarini
• Anthony Kwasnica
• David Pennock

Explainably estimating confidence in published scholarly work offers opportunity for faster and more robust scientific progress. We develop a synthetic prediction market to assess the credibility of published claims in the social and behavioral sciences literature. We demonstrate our system and detail our findings using a collection of known replication projects. We suggest that this work lays the foundation for a research agenda that creatively uses AI for peer review.

AAMAS Conference 2019 Conference Paper

Incentivizing Distributive Fairness for Crowdsourcing Workers

• Chenxi Qiu
• Anna Squicciarini
• Benjamin Hanrahan

In a crowd market such as Amazon Mechanical Turk, the remuneration of Human Intelligence Tasks is determined by the requester, for which they are not given many cues to ascertain how to “fairly” pay their workers. Furthermore, the current methods for setting a price are mostly binary – in that, the worker either gets paid or not – as opposed to paying workers a “fair” wage based on the quality and utility of work completed. Instead, the price should better reflect the historical performance of the market and the requirements of the task. In this paper, we introduce a game theoretical model that takes into account a more balanced set of market parameters, and propose a pricing policy and a rating policy to incentivize requesters to offer “fair” compensation for crowdsourcing workers. We present our findings from applying and developing this model on real data gathered from workers on Amazon Mechanical Turk and simulations that we ran to validate our assumptions. Our simulation results also demonstrate that our policies motivate requesters to pay their workers more “fairly” compared with the payment set by the current market.

AAMAS Conference 2018 Conference Paper

Combating Behavioral Deviance via User Behavior Control

• Chenxi Qiu
• Anna Squicciarini
• Christopher Griffin
• Prasanna Umar

Compared to traditional behavioral deviance, online deviant behavior (like cyberbullying) is more likely to spread over online social communities since it is not restricted by time and space, and can occur more frequently and intensely. To control risks associated with the spread of deviant and anti-normative behavior, it is essential to understand online users’ reaction when they interact with other users. In this paper, we model online users’ behavior interaction as an evolutionary game on a graph and analyze users’ behavior dynamics under different network conditions. Based on this theoretical framework, we then investigate behavior control strategies that aim to eliminate behavioral deviance. Finally, we use a real world dataset from a social network to verify the accuracy of our model’s hypothesis. We also and test the performance of our behavior control strategy through simulations based on both real and synthetically generated data. The experimental results demonstrate that our behavior control methods can effectively eliminate the impact of bullying behavior even when the proportion of bullying messages is higher than 60%.

AAMAS Conference 2018 Conference Paper

CrowdEval: A Cost-Efficient Strategy to Evaluate Crowdsourced Worker's Reliability

• Chenxi Qiu
• Anna Squicciarini
• Dev Rishi Khare
• Barbara Carminati
• James Caverlee

Crowdsourcing platforms depend on the quality of work provided by a distributed workforce. Yet, it is challenging to dependably measure the reliability of these workers, particularly in the face of strategic or malicious behavior. In this paper, we present a dynamic and efficient solution to keep tracking workers’ reliability. In particular, we use both gold standard evaluation and peer consistency evaluation to measure each worker performance, and adjust the proportion of the two types of evaluation according to the estimated distribution of workers’ behavior (e. g. , being reliable or malicious). Through experiments over real Amazon Mechanical Turk traces, we find that our approach has a significant gain in terms of accuracy and cost compared to state-of-the-art algorithms.

AAAI Conference 2018 Short Paper

Uncovering Scene Context for Predicting Privacy of Online Shared Images

• Ashwini Tonge
• Cornelia Caragea
• Anna Squicciarini

With the exponential increase in the number of images that are shared online every day, the development of effective and efficient learning methods for image privacy prediction has become crucial. Prior works have used as features automatically derived object tags from images’ content and manually annotated user tags. However, we believe that in addition to objects, the scene context obtained from images’ content can improve the performance of privacy prediction. Hence, we propose to uncover scene-based tags from images’ content using convolutional neural networks. Experimental results on a Flickr dataset show that the scene tags and object tags complement each other and yield the best performance when used in combination with user tags.

IJCAI Conference 2017 Conference Paper

A Group-Based Personalized Model for Image Privacy Classification and Labeling

• Haoti Zhong
• Anna Squicciarini
• David Miller
• Cornelia Caragea

We address machine prediction of an individual's label (private or public) for a given image. This problem is difficult due to user subjectivity and inadequate labeled examples to train individual, personalized models. It is also time and space consuming to train a classifier for each user. We propose a Group-Based Personalized Model for image privacy classification in online social media sites, which learns a set of archetypical privacy models (groups), and associates a given user with one of these groups. Our system can be used to provide accurate ``early warnings'' with respect to a user's privacy awareness level.

AAMAS Conference 2017 Conference Paper

Consensus on Social Graphs under Increasing Peer Pressure

• Justin Semonsen
• Christopher Griffin
• Anna Squicciarini
• Sarah Rajtmajer

AAMAS Conference 2016 Conference Paper

Constrained Social-Energy Minimization for Multi-Party Sharing in Online Social Networks

• Sarah Rajtmajer
• Anna Squicciarini
• Christopher Griffin
• Sushama Karumanchi
• Alpana Tyagi

The development of fair and practical policies for shared content online is a primary goal of the access control community. Multi-party access control, in which access control policies are determined by multiple users each with vested interest in a piece of shared content, remains an outstanding challenge. Purposeful or accidental disclosures by one user in an online social network (OSN) may have negative consequences for others, highlighting the importance of appropriate sharing mechanisms. In this work, we develop a game-theoretic framework for modeling multi-party privacy decisions for shared content. We assume that the content owner (uploader) selects an initial privacy policy that constrains the privacy settings of other users. We prove the convergence of users’ access control policies assuming a multi-round consensus-building game in which all players are fully rational and investigate a variation of rational play that better describes user behavior and also leads to the rational equilibrium. Additionally, in an effort to better approximate human behavior, we study a bounded rationality model and simulate real user choices in this context. Finally, we validate model assumptions and conclusions using experimental data obtained through a study of 95 individuals in a mock-social network. CCS Concepts •Security and privacy → Social network security and privacy; Economics of security and privacy; Social aspects of security and privacy; •Human-centered computing → Social content sharing; Social networks; Social media; Social tagging systems; Synchronous editors; •Theory of computation → Network games; Algorithmic game theory; Appears in: Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016), J. Thangarajah, K. Tuyls, C. Jonker, S. Marsella (eds.), May 9–13, 2016, Singapore. Copyright c 2016, International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). All rights reserved.

IJCAI Conference 2016 Conference Paper

Content-Driven Detection of Cyberbullying on the Instagram Social Network

• Haoti Zhong
• Hao Li
• Anna Squicciarini
• Sarah Rajtmajer
• Christopher Griffin
• David Miller
• Cornelia Caragea

We study detection of cyberbullying in photo-sharing networks, with an eye on developing early warning mechanisms for the prediction of posted images vulnerable to attacks. Given the overwhelming increase in media accompanying text in online social networks, we investigate use of posted images and captions for improved detection of bullying in response to shared content. We validate our approaches on a dataset of over 3000 images along with peer-generated comments posted on the Instagram photo-sharing network, running comprehensive experiments using a variety of classifiers and feature sets. In addition to standard image and text features, we leverage several novel features including topics determined from image captions and a pretrained convolutional neural network on image pixels. We identify the importance of these advanced features in assisting detection of cyberbullying in posted comments. We also provide results on classification of images and captions themselves as potential targets for cyberbullies.