No abstract

Our work considers leveraging crowd signals for detecting fake news and is motivated by tools recently introduced by Facebook that enable users to flag fake news. By aggregating users' flags, our goal is to select a small subset of news every day, send them to an expert (e.g., via a third-party fact-checking organization), and stop the spread of news identified as fake by an expert. The main objective of our work is to minimize the spread of misinformation by stopping the propagation of fake news in the network. It is especially challenging to achieve this objective as it requires detecting fake news with high-confidence as quickly as possible. We show that in order to leverage users' flags efficiently, it is crucial to learn about users' flagging accuracy. We develop a novel algorithm, Detective, that performs Bayesian inference for detecting fake news and jointly learns about users' flagging accuracy over time. Our algorithm employs posterior sampling to actively trade off exploitation (selecting news that maximize the objective value at a given epoch) and exploration (selecting news that maximize the value of information towards learning about users' flagging accuracy). We demonstrate the effectiveness of our approach via extensive experiments and show the power of leveraging community signals for fake news detection.

Bike sharing systems have been recently adopted by a growing number of cities as a new means of transportation offering citizens a flexible, fast and green alternative for mobility. Users can pick up or drop off the bicycles at a station of their choice without prior notice or time planning. This increased flexibility comes with the challenge of unpredictable and fluctuating demand as well as irregular flow patterns of the bikes. As a result, these systems can incur imbalance problems such as the unavailability of bikes or parking docks at stations. In this light, operators deploy fleets of vehicles which re-distribute the bikes in order to guarantee a desirable service level. Can we engage the users themselves to solve the imbalance problem in bike sharing systems? In this paper, we address this question and present a crowdsourcing mechanism that incentivizes the users in the bike repositioning process by providing them with alternate choices to pick or return bikes in exchange for monetary incentives. We design the complete architecture of the incentives system which employs optimal pricing policies using the approach of regret minimization in online learning. We investigate the incentive compatibility of our mechanism and extensively evaluate it through simulations based on data collected via a survey study. Finally, we deployed the proposed system through a smartphone app among users of a large scale bike sharing system operated by a public transport company, and we provide results from this experimental deployment. To our knowledge, this is the first dynamic incentives system for bikes re-distribution ever deployed in a real-world bike sharing system.

Web search queries reveal extensive information about users' personal lives to the search engines and Internet eavesdroppers. Obfuscating search queries through adding dummy queries is a practical and user-centric protection mechanism to hide users' search intentions and interests. Despite few such obfuscation methods and tools, there is no generic quantitative methodology for evaluating users' web-search privacy. In this paper, we provide such a methodology. We formalize adversary's background knowledge and attacks, the users' privacy objectives, and the algorithms to evaluate effectiveness of query obfuscation mechanisms. We build upon machine-learning algorithms to learn the linkability between user queries. This encompasses the adversary's knowledge about the obfuscation mechanism and the users' web-search behavior. Then, we quantify privacy of users with respect to linkage attacks. Our generic attack can run against users for which the adversary does not have any background knowledge, as well as for the cases where some prior queries from the target users are already observed. We quantify privacy at the query level (the link between user's queries) and the semantic level (user's topics of interest). We design a generic tool that can be used for evaluating generic obfuscation mechanisms, and users with different web search behavior. To illustrate our approach in practice, we analyze and compare privacy of users for two example obfuscation mechanisms on a set of real web-search logs.

We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL learner to speed up the learning process? We present an interactive teaching framework where a teacher adaptively chooses the next demonstration based on learner's current policy. In particular, we design teaching algorithms for two concrete settings: an omniscient setting where a teacher has full knowledge about the learner's dynamics and a blackbox setting where the teacher has minimal knowledge. Then, we study a sequential variant of the popular MCE-IRL learner and prove convergence guarantees of our teaching algorithm in the omniscient setting. Extensive experiments with a car driving simulator environment show that the learning progress can be speeded up drastically as compared to an uninformative teacher.

Search engines return ranked lists of Web pages in response to queries. These pages are starting points for post-query navigation, but may be insufficient for search tasks involving multiple steps. Search trails mined from toolbar logs start with a query and contain pages visited by one user during post-query navigation. Implicit endorsements from many trails can enhance result ranking. Rather than using trails solely to improve ranking, it may also be worth providing trail information directly to users. In this paper, we quantify the benefit that users currently obtain from trailfollowing and compare different methods for finding the best trail for a given query and each top-ranked result. We compare the relevance, topic coverage, topic diversity, and utility of trails selected using different methods, and break out findings by factors such as query type and origin relevance. Our findings demonstrate value in trails, highlight interesting differences in the performance of trailfinding algorithms, and show we can find best-trails for a query that outperform the trails most users follow. Findings have implications for enhancing Web information seeking using trails.

We study the sample complexity of teaching, termed as ``teaching dimension" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstration paradigm motivated by robotics applications, where the teacher teaches by providing demonstrations of state/action trajectories. The teaching-by-reinforcement paradigm applies to a wider range of real-world settings where a demonstration is inconvenient, but has not been studied systematically. In this paper, we focus on a specific family of reinforcement learning algorithms, Q-learning, and characterize the TDim under different teachers with varying control power over the environment, and present matching optimal teaching algorithms. Our TDim results provide the minimum number of samples needed for reinforcement learning, and we discuss their connections to standard PAC-style RL sample complexity and teaching-by-demonstration sample complexity results. Our teaching algorithms have the potential to speed up RL agent learning in applications where a helpful teacher is available.

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine which of the two is more unfair? Our core idea is to use existing inequality indices from economics to measure how unequally the outcomes of an algorithm benefit different individuals or groups in a population. Our work offers a justified and general framework to compare and contrast the (un)fairness of algorithmic predictors. This unifying approach enables us to quantify unfairness both at the individual and the group level. Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component. Earlier methods are typically designed to tackle only between-group unfairness, which may be justified for legal or other reasons. However, we demonstrate that minimizing exclusively the between-group component may, in fact, increase the within-group, and hence the overall unfairness. We characterize and illustrate the tradeoffs between our measures of (un)fairness and the prediction accuracy.