Daniele Quercia

Recommending Social Events from Mobile Phone Location Data

A city offers thousands of social events a day, and it is difficult for dwellers to make choices. The combination of mobile phones and recommender systems can change the way one deals with such abundance. Mobile phones with positioning technology are now widely available, making it easy for people to broadcast their whereabouts, recommender systems can now identify patterns in people’s movements in order to, for example, recommend events. To do so, the system relies on having mobile users who share their attendance at a large number of social events: cold-start users, who have no location history, cannot receive recommendations. We set out to address the mobile cold-start problem by answering the following research question: how can social events be recommended to a cold-start user based only on his home location? To answer this question, we carry out a study of the relationship between preferences for social events and geography, the first of its kind in a large metropolitan area. We sample location estimations of one million mobile phone users in Greater Boston, combine the sample with social events in the same area, and infer the social events attended by 2,519 residents. Upon this data, we test a variety of algorithms for recommending social events. We find that the most effective algorithm recommends events that are popular among residents of an area. The least effective, instead, recommends events that are geographically close to the area. This last result has interesting implications for location-based services that emphasize recommending nearby events.

B-Trust: bayesian trust framework for pervasive computing

Without trust, pervasive devices cannot collaborate effectively, and without collaboration, the pervasive computing vision cannot be made a reality. Distributed trust frameworks may support trust and thus foster collaboration in an hostile pervasive computing environment. Existing frameworks deal with foundational properties of computational trust. We here propose a distributed trust framework that satisfies a broader range of properties. Our framework: (i) evolves trust based on a Bayesian formalization, whose trust metric is expressive, yet tractable; (ii) is lightweight; (iii) protects user anonymity, whilst being resistant to “Sybil attacks” (and enhancing detection of two collusion attacks); (iv) integrates a risk-aware decision module. We evaluate the framework through four experiments.

Lightweight Distributed Trust Propagation

Using mobile devices, such as smart phones, people may create and distribute different types of digital content (e.g., photos, videos). One of the problems is that digital content, being easy to create and replicate, may likely swamp users rather than informing them. To avoid that, users may organize content producers that they know and trust in a web of trust. Users may then reason about this web of trust to form opinions about content producers with whom they have never interacted before. These opinions will then determine whether content is accepted. The process of forming opinions is called trust propagation. We design a mechanism for mobile devices that effectively propagates trust and that is lightweight and distributed (as opposed to previous work that focuses on centralized propagation). This mechanism uses a graph-based learning technique. We evaluate the effectiveness (predictive accuracy) of this mechanism against a large real-world data set. We also evaluate the computational cost of a J2ME implementation on a mobile phone.

TRULLO - local trust bootstrapping for ubiquitous devices

Handheld devices have become sufficiently powerful that it is easy to create, disseminate, and access digital content (e.g., photos, videos) using them. The volume of such content is growing rapidly and, from the perspective of each user, selecting relevant content is key. To this end, each user may run a trust model - a software agent that keeps track of who disseminates content that its user finds relevant. This agent does so by assigning an initial trust value to each producer for a specific category (context); then, whenever it receives new content, the agent rates the content and accordingly updates its trust value for the producer in the content category. However, a problem with such an approach is that, as the number of content categories increases, so does the number of trust values to be initially set. This paper focuses on how to effectively set initial trust values. The most sophisticated of the current solutions employ predefined context ontologies, using which initial trust in a given context is set based on that already held in similar contexts. However, universally accepted (and time invariant) ontologies are rarely found in practice. For this reason, we propose a mechanism called TRULLO (trust bootstrapping by latently lifting context) that assigns initial trust values based only on local information (on the ratings of its users past experiences) and that, as such, does not rely on third-party recommendations. We evaluate the effectiveness of TRULLO by simulating its use in an informal antique market setting. We also evaluate the computational cost of a J2ME implementation of TRULLO on a mobile phone.

TATA: towards anonymous trusted authentication

Mobile devices may share resources even in the presence of untrustworthy devices. To do so, each device may use a computational model that on input of reputation information produces trust assessments. Based on such assessments, the device then decides with whom to share: it will likely end up sharing only with the most trustworthy devices, thus isolating the untrustworthy ones. All of this is, however, theoretical in the absence of a general and distributed authentication mechanism. Currently, distributed trust frameworks do not offer an authentication mechanism that supports user privacy, whilst being resistant to “Sybil attacks”. To fill the gap, we first analyze the general attack space that relates to anonymous authentication as it applies to distributed trust models. We then put forward a scheme that is based on blinded threshold signature: collections of devices certify pseudonyms without seeing them and without relying on a central authority. We finally discuss how the scheme tackles the authentication attacks.

Performance analysis of Distributed Speech Recognition over IP networks on the AURORA database

We present results on the performance of Distributed Speech Recognition operating over simulated IP networks. ETSI AURORA front-end running at client nodes extracts the speech parameters, packetizes and sends them as real-time IP traffic to a remote recognizer based on Continuous Density Hidden Markov Models. The experimental framework is the ETSI STQ-AURORA Project Database 2.0. The impact of transmission over IP networks is modeled by (1) random losses, (2) losses generated by a Gilbert model and (3) network simulations. Results show that random losses and moderately bursty losses do not significantly affect the recognition performance. Strongly bursty packet losses, as those generated by real-time and Web traffic competing over a network bottleneck, instead, can have a very negative impact on recognition performance, indicating that DSR over the Internet, to be successful, requires high levels of Quality of Service.

MOTET: Mobile Transactions using Electronic Tickets

There has been considerable work within the field of digital cash protocols that aims to provide security guarantees - non-repudiation, authentication, overspending checking and off-line checking - whilst protecting anonymity. However, considerably less attention has been given to the question of electronic ticketing, and what exists has been rather abstract or limited. Although eTickets aim at providing the same security guarantees and privacy preservation properties as digital cash, they are significantly different. Digital cash derives much of its anonymity from the fact that the denominations of electronic coins and notes are sufficiently universal that it is not possible for the bank to know in advance how they might be spent. In an eTicketing system, however, this is not the case: at the point the ticket is purchased, the ticket vendor knows for what it will be used and, if a non-anonymous payment system is used, can associate this with the customer. We present a novel protocol that enables users to purchase and spend electronic tickets (eTickets) of a range of two different types: those that can only be used a certain number of times, and those that expire after a certain date.

MobiRate: making mobile raters stick to their word

To share services, portable devices may need to locate reputable in-range providers and, to do so, they may exchange ratings with each other. However, providers may well tweak ratings to their own advantage. That is why we have designed a new decentralized mechanism (dubbed MobiRate) with which portable devices store ratings in (local) tamperevident tables and check the integrity of those tables through a gossiping protocol. We evaluate the extent to which MobiRate reduces the impact of tampered ratings and consequently locates reputable service providers. We do so using real mobility and social network data. We also assess computational and communication costs of MobiRate on mobile phones.

A statistical matching approach to detect privacy violation for trust-based collaborations

Distributed trust and reputation management mechanisms are often proposed as a means of providing assurance in dynamic and open environments by enabling principals to building up knowledge of the entities with which they interact. However, there is a tension between the preservation of privacy (which would suggest a refusal to release information) and the controlled release of information that is necessary both in order to accomplish tasks and to provide a foundation for the assessment of trustworthiness. However, if reputation-based systems are to be used in assessing the risks of privacy violation, it is necessary both to discover when sensitive information has been released, and then to be able to evaluate the likelihood that each of the set of principals that knew that information was involved in its release. We argue that statistical traceability can act as a basis for reaching a proper balance between privacy and trust. To enable this, we assume that interacting principals negotiate service level agreements that are intended to constrain the ways in which personal information may be used, and then monitor violations, ascribing likelihoods of involvement in release using an approach based on statistical disclosure control. Even though our approach cannot guarantee perfect privacy protection for personal information, it provides a framework using which detected privacy violation can be mapped onto a measure of accountability, which is useful in deterring such violation.

Diversity of indoor activities and economic development of neighborhoods

Over the last few decades, public life has taken center stage in urban studies, but that is about to change. At times, indoor activities have been shown to matter more than what is publicly visible (they have been found to be more predictive of future crimes, for example). Until recently, however, data has not been available to study indoor activities at city scale. To that end, we propose a new methodology that relies on tagging information of geo-referenced pictures and unfolds in three main steps. First, we collected and classified a comprehensive set of activity-related words, creating the first dictionary of urban activities. Second, for both London and New York City, we collected geo-referenced Flickr tags and matched them with the words in the dictionary. This step produced both a systematic classification (our activity-related words were best classified in eleven categories) and two city-wide indoor activity maps which, when compared to open data of public amenities and sensory maps of smell and sound matched theoretical expectations. Third, we studied, for the first time, activities happening indoor in relation to neighborhood socio-economic conditions. We found the very same result for both London and New York City. In deprived areas, people focused on any of the activity types (leading to specialization), and it did not matter on which one they did so. By contrast, in well-to-do areas, people engaged not in one type of activity but in a variety of them (leading to diversification).