Uncertainty-aware Personal Assistant and Explanation Method for Privacy Decisions

This paper investigates the relationship between individuals’ heterogeneous risk attitudes and privacy preferences using survey data from 24,899 respondents. It moves beyond demographic factors to examine how risk attitudes, the key psychological parameters in the utility function that determines consumer behaviors, related to consumers’ privacy decisions. Participants indicated their privacy preferences across eight dimensions, including age privacy, marital status privacy, and privacy preferences in the investment and financial obligation realms. We evaluated their risk attitudes through qualitative assessment and quantitative investment loss tolerances, as well as their risk attitudes towards rare and distant events. The study reveals that individuals with higher risk aversion exhibit more significant privacy concerns, especially regarding financial information. Individuals who perceive climate change—a non-immediate and rare risk—as a threat to their lives are also more likely to exhibit heightened concerns about their privacy. In addition, we observe that while these concerns translate into higher non-disclosure actions, the privacy paradox persists regardless of individuals’ risk attitudes. The findings suggest that privacy policies could be more effective through tailored approaches, including customized privacy settings and targeted educational campaigns that account for individual risk aversion.

Recent advances in mobile devices and their sensing capabilities have enabled the collection of rich contextual information and mobile device usage records through the device logs. These context-rich logs open a venue for mining the personal preferences of mobile users under varying contexts and thus enabling the development of personalized context-aware recommendation and other related services, such as mobile online advertising. In this article, we illustrate how to extract personal context-aware preferences from the context-rich device logs, or context logs for short, and exploit these identified preferences for building personalized context-aware recommender systems. A critical challenge along this line is that the context log of each individual user may not contain sufficient data for mining his or her context-aware preferences. Therefore, we propose to first learn common context-aware preferences from the context logs of many users. Then, the preference of each user can be represented as a distribution of these common context-aware preferences. Specifically, we develop two approaches for mining common context-aware preferences based on two different assumptions, namely, context-independent and context-dependent assumptions, which can fit into different application scenarios. Finally, extensive experiments on a real-world dataset show that both approaches are effective and outperform baselines with respect to mining personal context-aware preferences for mobile users.

Typical tag recommendation systems for photos shared on social networks such as Flickr, use visual content analysis, collaborative filtering or personalization strategies to produce annotations. However, the dependence on manual intervention and the knowledge of sufficient personal preferences coupled with the folksonomic issues limit the scope of these strategies. In this paper, we present a fully automatic and folksonomically scalable tag recommendation model that can recommend tags for a user's photos without an explicit knowledge of the user's personal tagging preferences. The model is learned using the collective tagging behavior of other users in the user's local interaction network, which we believe approximates the user's preferences, at least partially. The tag recommendation model generates content-based annotations and then uses a Naive Bayes formulation to translate these annotations to a set of folksonomic tags selected from the tags used by the users in the local interaction network. Quantitative and qualitative comparisons with 890 Flickr networks show that this approach is highly useful for tag recommendation in the presence of insufficient information of a user's own preferences.

More and more users openly share their information on online websites, with the resulting privacy issues being under scrutiny. Content such as a user’s personal data and location information is often asked for before posting to enforce the user’s privacy preferences; however, little attention has been paid to the lack of content (e.g., images) posted by the user. Even if privacy preferences are requested before images are published, publishers often remain unaware of the extent of privacy leakage associated with their data. To this end, we provide an image privacy metric scheme that incorporates users’ privacy preferences, with the core idea of assisting users in making data publishing decisions. First, we propose privacy-specific spatial attention mechanisms that can effectively improve the prediction accuracy. Next, we integrate set pair analysis (SPA) theory and use the network output as the privacy value. Finally, we combine a user study to understand the privacy preferences of different users with respect to these attributes and combine it with principal component analysis to correct and enforce user privacy preferences. Our model is trained with the ability to predict privacy risk end-to-end, thus being able to guide the user in sharing data in open platforms. We use the image privacy dataset, VISPR, to predict privacy information better than other methods.

The aim of personalizing web information systems is to tailor content (media) to the user's personal preferences, goals and context, in turn increasing the reusability of that content. However, most developers are increasingly seeking to apply 'Web as a Platform' based approaches where web-based content is integrated with web services to provide the platform and environment features that were traditionally offered by desktop environments and applications. Therefore, next generation personalized web information systems need to be capable of dynamically personalizing, adapting and integrating web content and web services to create customized experiences for individual users. The goal of the research presented in this paper is to provide innovative techniques and technologies to achieve this. As part of this research, a novel architecture for the generation of Personalized Learning Activities, which highlights both the need for, and the power of combining and personalizing content and services has been developed. The system has been evaluated in the context of a Higher Education use case based on the user's perception of three key elements of the Personalized Learning Activity: the personalization, the usability and the educational benefits.

In this paper we present a Japanese-English transfer- based machine translation system. Our main research contribution is that the transfer rules are not handcrafted but are learnt automatically from a parallel corpus. We learn specific transfer rules from sentence pairs, which are then generalized in a consolidation phase to avoid overtraining. The system has been implemented in Amzi! Prolog, which offers scalability for large rule bases, full Unicode support for Japanese characters, and several APIs for the seamless integration of the translation functionality into common office environments, e.g. Microsoft Word. The dynamic nature of our system allows for an easy customization of the rule base according to the user's personal preferences.

In order to identify a user's personal preference in navigating the Web or to recommend collected Web information, it is very useful to analyze the user's Web-browsing behavior. However, it is difficult to determine which Web-browsing behaviors are influential on predicting a user's interest because each individual has his/her own habit and personal manner in surfing the Web and locating documents of interest. In this study, we propose an adaptive personalized recommender system based on a preference-thesaurus constructed by learning a user's Web-browsing behavior. The major components of the proposed recommender system are the Web-browsing behavior monitor, preference-thesaurus constructor, relevant document recommender, and user feedback learner. The adaptive nature of the proposed system allows the personalization of recommendation and the identification of the ever-changing influential Web-browsing behaviors. A proof-of-concept system is implemented and experiments are performed to verify the system's capability to personalize recommendation and to learn through user's feedbacks.

Today's software offers diverse functionalities that need to be made accessible to humans in an easy to understand and quick to learn way. This is not a new challenge and already well addressed in usability research. Yet, similar challenges arise in crowdsourcing tasks. While task interfaces are often less complicated than complete software products, crowdsourcing workers have only a minimal amount of time to familiarize them with the task interface. Additionally, due to the repetitiveness of the tasks, workers are required to work with this interface to solve a few hundred tasks. Unfortunately, often little attention is paid to optimize the task interfaces. Even if recent studies have shown evidence of the negative effects of poorly designed interfaces on the work performance, there is less knowledge about the importance of the usability from the worker's point of view and their personal preferences. This work aims to fill this gap in two steps. First, we analyze the relevance of good usability and interface design in relation to other task properties like payment or joyfulness by conducting a survey on two popular crowdsourcing platforms. Second, we identify interface properties that are of importance for the crowdsourcing workers and discuss both consenting and dissenting opinions of different worker groups. The results show that all workers place an essential role in the usability of a task interface when selecting tasks, but do not agree on coherent design preferences within and between the platforms.

Nowadays, privacy protection in web applications and services is done, most times, through privacy policies that are presented to users and give them only the options of agreeing or disagreeing. So, it is not possible for users to express, in a detailed manner, their privacy preferences. Having this flexibility would allow users to make more thoughtful choices about the use of their personal information online. This paper proposes a database framework that allows users express their privacy preferences in detail, so that web applications can protect data privacy and manage personal information more securely. We tested the framework and results showed that it can be a simple and effective alternative, avoiding using complex and expensive solutions.

Shared mobility can fundamentally change road transport and improve life quality. Car-sharing services have reached a high level of growth worldwide and members adopting them as an alternative transportation mode are constantly on the increase. The advent of highly automated vehicles could boost the adoption of car sharing as more inexpensive and convenient on-demand services could be achieved. In recent years, vehicle automation is facilitated and supported by the latest advances in information and communication technologies, forming the cornerstone of the new generation of In-Vehicle Intelligent Systems. The goal of this study is to introduce a novel in-vehicle cognitive framework that utilises (i) driver's/user's profile data and personal preferences, (ii) real-time information associated with the vehicle's driving environment, and (iii) previous knowledge and experience, in proposing adaptations of the vehicle's level of autonomy, in an automated manner, when a driver/user wishes to make a road journey within the automated vehicle sharing context. Knowledge is obtained through the exploitation of Bayesian networking principles. Indicative results on the performance of the proposed cognitive mechanism and the associated knowledge-based selection scheme are presented, mostly with regards to proactively identifying the optimum level of autonomy to be implemented.

In this paper, we discuss how a short-range wireless communication scheme called Mobile Encounter Network (MEN) can provide additional value for both the consumer and the service/product provider (the company). When used as an information search system on the market environment, a MEN-based system allows services and products being promoted at the location they are available. From the customer's point of view, MEN may provide a digitally augmented vision, an enhanced view to the current environment. Combined with a set of filtering and search rules this may provide a self-manageable context combining the user's own personal environment and preferences to the services and features available in the current surroundings. An imaginary case study of this kind of system in execution is provided. The conclusion is that such method may can generate additional revenue to the company and please the customers' buying process.

In this paper, we introduce MyCampus, a Semantic Web environment for context-aware mobile services, which we are in the process of developing and validating on Carnegie Mellon University's campus. The environment revolves around a growing collection of customizable agents capable of (semi-) automatically discovering and accessing user personal resources (e.g. calendar, location tracking functionality, food preferences) and Web services as they assist their users in carrying out different tasks such as planning an evening out, organizing a study group or filtering incoming messages. The openness of the MyCampus architecture directly derives from a set of ontologies for describing personal resources, contextual attributes, user preferences and web services. Contextual information and other personal details about a user are accessed via a Semantic e-Wallet, subject to access privileges set by the user.

There is a buzz about the new lightweight software development processes. These processes are certainly capable of creating successful software systems faster. As a software developer, which one should you choose for your project? Indeed, today's software development processes bring interesting dynamics to the projects to which developers apply them. But should process drive the project or should the project determine the process? I examine one characteristic of these processes, scalability, which can help you decide what process is best for you.

While management of today's software systems is usually performed by humans using some user interface (UI), autonomic systems would be self-managed. They would typically consist of a managed element, which provides actual system functionality, and an autonomic manager performing system management. However, truly self-managed systems are hard to achieve and not (yet) in wide-spread use. During the transition towards autonomic software systems it is more realistic to manage a large and complex software system partly by humans and partly by an autonomic manager. For facilitating this approach, the communication between the managed element and human administrators on the one hand and the communication between the managed element and the autonomic manager on the other, should be unified and specified on the same semantic level. However, there is no scientific basis for such a unified communication approach.We present a unified specification of this communication in a high-level discourse model based on insights from theories of human communication. This approach would make this communication natural for humans to define and to understand. In addition, we propose to use the same specification for the automated generation of user interfaces for management by human administrators. As a consequence, a smooth and gradual transition towards self-managed software systems will be facilitated, where the portion managed by human administrators becomes smaller and smaller.

Today, users interact with a variety of online services offered by different providers. In order to supply their services, providers collect, store and process users' data according to their privacy policies. To have more control on personal data, user can specify a set of privacy preferences, encoding the conditions according to which his/her data can be used and managed by the provider. Moreover, many services are context dependent, that is, the type of delivered service is based on user contextual information (e.g., time, location, and so on). This makes more complicated the definition of privacy preferences, as, typically, users might have different attitude with respect the privacy management based on the current context (e.g., working hour, free time). To provide a more fine-grained control, a user can set up different privacy preferences for each different possible contexts. However, since user change the context very frequently, this might result in a very complex and time-consuming task. To cope with this issue, in this paper, we propose a context-based privacy management service that helps users to manage their privacy preferences setting under different contexts. At this aim, we exploit machine learning algorithms to build a classifier, able to infer new privacy preferences for the new context. The preliminary experimental results we have conducted are promising, and show the effectiveness of the proposed approach.