Alexandra Olteanu

What to Expect When the Unexpected Happens: Social Media Communications Across Crises

The use of social media to communicate timely information during crisis situations has become a common practice in recent years. In particular, the one-to-many nature of Twitter has created an opportunity for stakeholders to disseminate crisis-relevant messages, and to access vast amounts of information they may not otherwise have. Our goal is to understand what affected populations, response agencies and other stakeholders can expect-and not expect-from these data in various types of disaster situations. Anecdotal evidence suggests that different types of crises elicit different reactions from Twitter users, but we have yet to see whether this is in fact the case. In this paper, we investigate several crises-including natural hazards and human-induced disasters-in a systematic manner and with a consistent methodology. This leads to insights about the prevalence of different information types and sources across a variety of crisis situations.

Web credibility: features exploration and credibility prediction

The open nature of the World Wide Web makes evaluating webpage credibility challenging for users. In this paper, we aim to automatically assess web credibility by investigating various characteristics of webpages. Specifically, we first identify features from textual content, link structure, webpages design, as well as their social popularity learned from popular social media sites (e.g., Facebook, Twitter). A set of statistical analyses methods are applied to select the most informative features, which are then used to infer webpages credibility by employing supervised learning algorithms. Real dataset-based experiments under two application settings show that we attain an accuracy of 75% for classification, and an improvement of 53% for the mean absolute error (MAE), with respect to the random baseline approach, for regression.

Quantifying the Effect of Co-Location Information on Location Privacy

Mobile users increasingly report their co-locations with other users, in addition to revealing their locations to online services. For instance, they tag the names of the friends they are with, in the messages and in the pictures they post on social networking websites. Combined with (possibly obfuscated) location information, such co-locations can be used to improve the inference of the users’ locations, thus further threatening their location privacy: as co-location information is taken into account, not only a user’s reported locations and mobility patterns can be used to localize her, but also those of her friends (and the friends of their friends and so on). In this paper, we study this problem by quantifying the effect of co-location information on location privacy, with respect to an adversary such as a social network operator that has access to such information. We formalize the problem and derive an optimal inference algorithm that incorporates such co-location information, yet at the cost of high complexity. We propose two polynomial-time approximate inference algorithms and we extensively evaluate their performance on a real dataset. Our experimental results show that, even in the case where the adversary considers co-locations with only a single friend of the targeted user, the location privacy of the user is decreased by up to 75% in a typical setting. Even in the case where a user does not disclose any location information, her privacy can decrease by up to 16% due to the information reported by other users.

A decentralized recommender system for effective web credibility assessment

An overwhelming and growing amount of data is available online. The problem of untrustworthy online information is augmented by its high economic potential and its dynamic nature, e.g. transient domain names, dynamic content, etc. In this paper, we address the problem of assessing the credibility of web pages by a decentralized social recommender system. Specifically, we concurrently employ i) item-based collaborative filtering (CF) based on specific web page features, ii) user-based CF based on friend ratings and iii) the ranking of the page in search results. These factors are appropriately combined into a single assessment based on adaptive weights that depend on their effectiveness for different topics and different fractions of malicious ratings. Simulation experiments with real traces of web page credibility evaluations suggest that our hybrid approach outperforms both its constituent components and classical content-based classification approaches.

Distilling the Outcomes of Personal Experiences: A Propensity-scored Analysis of Social Media

Millions of people regularly report the details of their real-world experiences on social media. This provides an opportunity to observe the outcomes of common and critical situations. Identifying and quantifying these outcomes may provide better decision-support and goal-achievement for individuals, and help policy-makers and scientists better understand important societal phenomena. We address several open questions about using social media data for open-domain outcome identification: Are the words people are more likely to use after some experience relevant to this experience? How well do these words cover the breadth of outcomes likely to occur for an experience? What kinds of outcomes are discovered? Studying 3-months of Twitter data capturing people who experienced 39 distinct situations across a variety of domains, we find that these outcomes are generally found to be relevant (55-100% on average) and that causally related concepts are more likely to be discovered than conceptual or semantically related concepts.

CredibleWeb: a platform for web credibility evaluation

The web content is the main source of information for many users. However, due to the open nature of todays web anyone can produce and publish content, which, as a result, is not always reliable. As such, mechanisms to evaluate the web content credibility are needed. In this paper, we describe CredibleWeb, a prototype crowdsourcing platform for web content evaluation with a two-fold goal: (1) to build a social enhanced and large scale dataset of credibility labeled web pages that enables the evaluation of different strategies for web credibility prediction, and (2) to investigate how various design elements are useful in engaging users to actively evaluate web pages credibility. We outline the challenges related with the design of a crowdsourcing platform for web credibility evaluation and describe our initial efforts.

Comparing the Predictive Capability of Social and Interest Affinity for Recommendations

The advent of online social networks created new prediction opportunities for recommender systems: instead of relying on past rating history through the use of collaborative filtering (CF), they can leverage the social relations among users as a predictor of user tastes similarity. Alas, little effort has been put into understanding when and why (e.g., for which users and what items) the social affinity (i.e., how well connected users are in the social network) is a better predictor of user preferences than the interest affinity among them as algorithmically determined by CF, and how to better evaluate recommendations depending on, for instance, what type of users a recommendation application targets. This overlook is explained in part by the lack of a systematic collection of datasets including both the explicit social network among users and the collaborative annotated items. In this paper, we conduct an extensive empirical analysis on six real-world publicly available datasets, which dissects the impact of user and item attributes, such as the density of social ties or item rating patterns, on the performance of recommendation strategies relying on either the social ties or past rating similarity. Our findings represent practical guidelines that can assist in future deployments and mixing schemes.

Topick: Accurate Topic Distillation for User Streams

Users of todays information networks need to digest large amounts of data. Therefore, tools that ease the task of filtering the relevant content are becoming necessary. One way to achieve this is to identify the users who generate content in a certain topic of interest. However, due to the diversity and ambiguity of the shared information, assigning users to topics in an automatic fashion is challenging. In this demo, we present Topick, a system that leverages state of the art techniques and tools to automatically distill high-level topics for a given user. Topick exploits both the user stream and her profile information to accurately identify the most relevant topics. The results are synthesised as a set of stars associated to each topic, designed to give an intuition about the topics encompassed in the user streams and the confidence in the results. Our prototype achieves a precision of 70% or more, with a recall of 60%, relative to manual labeling. Topick is available at http://topick.alexandra.olteanu.eu.