According to Daniel Kahneman, there are two systems that drive the human decision making process: The intuitive system that performs the fast thinking, and the deliberative system that does more logical and slower thinking. Inspired by this model, we propose a framework for implementing human activity recognition on mobile devices. In this area, the mobile app is usually always-on and the general challenge is how to balance accuracy and energy consumption. However, among existing approaches, those based on cellular IDs consume little power but are less accurate; those based on GPS/WiFi sampling are accurate often at the costs of battery drainage; moreover, previous methods in general do not improve over time. To address these challenges, our framework consists of two modes: In the deliberation mode, the system learns cell ID patterns that are trained by existing GPS/WiFi based methods; in the intuition mode, only the learned cell ID patterns are used for activity recognition, which is both accurate and energy-efficient; system parameters are learned to control the transition from deliberation to intuition, when sufficient confidence is gained, and the transition from intuition to deliberation, when more training is needed. For the scope of this paper, we first elaborate our framework in a subproblem in activity recognition, trip detection, which recognizes significant places and trips between them. For evaluation, we collected real-life traces of six participants over five months. Our experiments demonstrated consistent results across different participants in terms of accuracy and energy efficiency, and, more importantly, its fast improvement on energy efficiency over time due to regularities in human daily activities.

I am delighted to announce that this project has come to fruition with the launch of the digital edition of AI Magazine. As each issue of the magazine is published, its digital edition will be delivered to subscribers by email. The digital edition is browser-based, making it accessible via the web, smartphone, or any modern web-enabled device. It provides the ability to quickly search, save, and share articles, as well as convenient options for navigating the magazine and seamlessly linking to other resources. The digital edition will enable substantial advances in the magazine's future design, such as the use of color throughout and the inclusion of embedded video, and over time the magazine will increasingly exploit this potential.

In photo-sharing websites and in social networks, photographs are most often browsed as a sequence: users who view a photo are likely to click on those that follow. The sequences of photos (which we call photostreams), as opposed to individual images, can therefore be considered to be very important content units in their own right. In spite of their importance, those sequences have received little attention even though they are at the core of how people consume image content. In this paper, we focus on photostreams. First, we perform an analysis of a large dataset of user logs containing over 100 million pageviews, examining navigation patterns between photostreams. Based on observations from the analysis, we build a stream transition graph to analyze common stream topic transitions (e.g., users often view “train” photostreams followed by “firetruck” photostreams). We then implement two stream recommendation algorithms, based on collaborative filtering and on photo tags, and report the results of a user study involving 40 participants. Our analysis yields interesting insights into how people navigate between photostreams, while the results of the user study provide useful feedback for evaluating the performance and characteristics of the recommendation algorithms.

Microblogs are increasingly gaining attention as an important information source in emergency management. In this case, state-of-the-art has shown that many valuable situational information is shared by citizens and official sources. However, current approaches focus on information shared during large scale incidents, with high amount of publicly available information. In contrast, in this paper, we conduct two studies on every day small scale incidents. First, we propose the first machine learning algorithm to detect three different types of small scale incidents with a precision of 82.2% and 82% recall. Second, we manually classify users contributing situational information about small scale incidents and show that a variety of individual users publish incident related information. Furthermore, we show that those users are reporting faster than official sources

The recent explosive growth of smart phones and social media creates a unique opportunity to view events from various unique perspectives. Unfortunately, this relatively new form of communication lacks the structural integrity, accuracy, and reduced noise of other forms of communication. Nevertheless, social media increasingly plays a vita role in the observation of societal actions before, during, and after significant events. In October 2012, Hurricane Sandy making landfall on the northeastern coasts of the United States demonstrated this role. This work provides a preliminary view into how social media could be used to monitor and gauge community resilience to such natural disasters. We observe, evaluate, and visualize how Twitter data evolves over time before, during, and after a natural disaster such as Hurricane Sandy and what opportunities there may be to leverage social media for situational awareness and emergency response.

This study focuses on the ways in which social technologies as a whole facilitate informal knowledge sharing in the workplace. Social technologies include both common technologies such as email, phone and instant messenger and emerging social networking technologies, often known as social media or Web 2.0, such as blogs, wikis, public social networking sites (i.e., Facebook, Twitter, and LinkedIn), enterprise social networking technologies, etc. To understand the role of social technologies in informal knowledge practices, we pursue a field study of knowledge workers in consulting firms to investigate the role of social technologies in their informal knowledge sharing practices. Findings highlight five knowledge practices motivated by different knowledge problems and supported by the use of multiple social technologies.

An important bottleneck in the development of accurate and robust personality recognition systems based on supervised machine learning, is the limited availability of training data, and the high cost involved in collecting it. In this paper, we report on a proof of concept of using ensemble learning as a way to alleviate the data acquisition problem. The approach allows the use of information from datasets from different genres, personality classification systems and even different languages in the construction of a classifier, thereby improving its performance. In the exploratory research described here, we indeed observe the expected positive effects.

Beyond being facilitators of human interactions, social networks have become an interesting target of research, providing rich information for studying and modeling user’s behavior. Identification of personality-related indicators encrypted in Facebook profiles and activities are of special concern in our current research efforts. This paper explores the feasibility of modeling user personality based on a proposed set of features extracted from the Facebook data. The encouraging results of our study, exploring the suitability and performance of several classification techniques, will also be presented.

Personality plays a fundamental role in human interaction. With the increasing amount of online user-generated content, automatic detection of a person's personality based on the text she produces is an important step to labeling and analyzing human behavior at a large scale. To date, most approaches to personality classification have modeled each personality trait in isolation (e.g., independent binary classification). In this paper, we instead model the dependencies between different personality traits using conditional random fields. Our study finds a correlation between Agreeableness and Emotional Stability traits that can improve Agreeableness classification. However, we also find that accuracy on other traits can degrade with this approach, due in part to the overall problem difficulty.

Gaining insight in a web user's personality is very valuable for applications that rely on personalisation, such as recommender systems and personalised advertising. In this paper we explore the use of machine learning techniques for inferring a user's personality traits from their Facebook status updates. Even with a small set of training examples we can outperform the majority class baseline algorithm. Furthermore, the results are improved by adding training examples from another source. This is an interesting result because it indicates that personality trait recognition generalises across social media platforms.