Philips Kokoh Prasetyo

Automatic classification of software related microblogs

Millions of people, including those in the software engineering communities have turned to microblogging services, such as Twitter, as a means to quickly disseminate information. A number of past studies by Treude et al., Storey, and Yuan et al. have shown that a wealth of interesting information is stored in these microblogs. However, microblogs also contain a large amount of noisy content that are less relevant to software developers in engineering software systems. In this work, we perform a preliminary study to investigate the feasibility of automatic classification of microblogs into two categories: relevant and irrelevant to engineering software systems. We extract features from the textual content of the microblogs and the titles of any URLs mentioned in the microblogs. These features are then used to learn a discriminative model used in classifying relevant and irrelevant microblogs. We show that our trained model can achieve a promising classification performance.

Collective Churn Prediction in Social Network

In service-based industries, churn poses a significant threat to the integrity of the user communities and profitability of the service providers. As such, research on churn prediction methods has been actively pursued, involving either intrinsic, user profile factors or extrinsic, social factors. However, existing approaches often address each type of factors separately, thus lacking a comprehensive view of churn behaviors. In this paper, we propose a new churn prediction approach based on collective classification (CC), which accounts for both the intrinsic and extrinsic factors by utilizing the local features of, and dependencies among, individuals during prediction steps. We evaluate our CC approach using real data provided by an established mobile social networking site, with a primary focus on prediction of churn in chat activities. Our results demonstrate that using CC and social features derived from interaction records and network structure yields substantially improved prediction in comparison to using conventional classification and user profile features only.

Mining indirect antagonistic communities from social interactions

Antagonistic communities refer to groups of people with opposite tastes, opinions, and factions within a community. Given a set of interactions among people in a community, we develop a novel pattern mining approach to mine a set of antagonistic communities. In particular, based on a set of user-specified thresholds, we extract a set of pairs of communities that behave in opposite ways with one another. We focus on extracting a compact lossless representation based on the concept of closed patterns to prevent exploding the number of mined antagonistic communities. We also present a variation of the algorithm using a divide and conquer strategy to handle large datasets when main memory is inadequate. The scalability of our approach is tested on synthetic datasets of various sizes mined using various parameters. Case studies on Amazon, Epinions, and Slashdot datasets further show the efficiency and the utility of our approach in extracting antagonistic communities from social interactions.

Social Sensing for Urban Crisis Management: The Case of Singapore Haze

Sensing social media for trends and events has become possible as increasing number of users rely on social media to share information. In the event of a major disaster or social event, one can therefore study the event quickly by gathering and analyzing social media data. One can also design appropriate responses such as allocating resources to the affected areas, sharing event related information, and managing public anxiety. Past research on social event studies using social media often focused on one type of data analysis (e.g., hashtag clusters, diffusion of events, influential users, etc.) on a single social media data source. This paper adopts a comprehensive social event analysis framework covering content, emotion, activity, and network. We propose a set of measures for each dimension accordingly. The usefulness of these analyses are demonstrated through a haze event that severely affected Singapore and its neighbors in June 2013. The analysis, conducted on both Twitter and Foursquare data, shows that much user attention was given to the haze event. The event also saw substantial emotional and behavioral impact on the social media users. These additional insights will help both public and private sectors to prepare themselves for future haze related events.

Mining direct antagonistic communities in signed social networks

Social networks provide a wealth of data to study relationship dynamics among people. Most social networks such as Epinions and Facebook allow users to declare trusts or friendships with other users. Some of them also allow users to declare distrusts or negative relationships. When both positive and negative links co-exist in a network, some interesting community structures can be studied. In this work, we mine Direct Antagonistic Communities (DACs) within such signed networks. Each DAC consists of two sub-communities with positive relationships among members of each sub-community, and negative relationships among members of the other sub-community. Identifying direct antagonistic communities is an important step to understand the nature of the formation, dissolution, and evolution of such communities. Knowledge about antagonistic communities allows us to better understand and explain behaviors of users in the communities. Identifying DACs from a large signed network is however challenging as various combinations of user sets, which is very large in number, need to be checked. We propose an efficient data mining solution that leverages the properties of DACs, and combines the identification of strongest connected components and bi-clique mining. We have experimented our approach on synthetic, myGamma, and Epinions datasets to showcase the efficiency and utility of our proposed approach. We show that we can mine DACs in less than 15min from a signed network of myGamma, which is a mobile social networking site, consisting of 600,000 members and 8million links. An investigation on the behavior of users participating in DACs shows that antagonism significantly affects the way people behave and interact with one another.

On Profiling Bots in Social Media

The popularity of social media platforms such as Twitter has led to the proliferation of automated bots, creating both opportunities and challenges in information dissemination, user engagements, and quality of services. Past works on profiling bots had been focused largely on malicious bots, with the assumption that these bots should be removed. In this work, however, we find many bots that are benign, and propose a new, broader categorization of bots based on their behaviors. This includes broadcast, consumption, and spam bots. To facilitate comprehensive analyses of bots and how they compare to human accounts, we develop a systematic profiling framework that includes a rich set of features and classifier bank. We conduct extensive experiments to evaluate the performances of different classifiers under varying time windows, identify the key features of bots, and infer about bots in a larger Twitter population. Our analysis encompasses more than 159K bot and human (non-bot) accounts in Twitter. The results provide interesting insights on the behavioral traits of both benign and malicious bots.

CNL: Collective Network Linkage Across Heterogeneous Social Platforms

The popularity of social media has led many users to create accounts with different online social networks. Identifying these multiple accounts belonging to same user is of critical importance to user profiling, community detection, user behavior understanding and product recommendation. Nevertheless, linking users across heterogeneous social networks is challenging due to large network sizes, heterogeneous user attributes and behaviors in different networks, and noises in user generated data. In this paper, we propose an unsupervised method, Collective Network Linkage (CNL), to link users across heterogeneous social networks. CNL incorporates heterogeneous attributes and social features unique to social network users, handles missing data, and performs in a collective manner. CNL is highly accurate and efficient even without training data. We evaluate CNL on linking users across different social networks. Our experiment results on a Twitter network and another Foursquare network demonstrate that CNL performs very well and its accuracy is superior than the supervised Mobius approach.

Socio-physical analytics: challenges & opportunities

In this paper, we argue for expanded research into an area called Socio-Physical Analytics, that focuses on combining the behavioral insight gained from mobile-sensing based monitoring of physical behavior with the inter-personal relationships and preferences deduced from online social networks. We highlight some of the research challenges in combining these heterogeneous data sources and then describe some examples of our ongoing work (based on real-world data being collected at SMU) that illustrate two aspects of socio-physical analytics: (a) how additional demographic and online analytics based attributes can potentially provide better insights into the preferences and behaviors of individuals or groups (in terms of movement prediction and understanding of physical vs. online interactions), and (b) how online and physical interactions can help us discover latent characteristics of physical spaces and entities.

A Business Zone Recommender System Based on Facebook and Urban Planning Data

We present ZoneRec—a zone recommendation system for physical businesses in an urban city, which uses both public business data from Facebook and urban planning data. The system consists of machine learning algorithms that take in a business’ metadata and outputs a list of recommended zones to establish the business in. We evaluate our system using data of food businesses in Singapore and assess the contribution of different feature groups to the recommendation quality.

On analyzing geotagged tweets for location-based patterns

Geotagged social media is becoming highly popular as social media access is now made very easy through a wide range of mobile apps which automatically detect and augment social media posts with geo-locations. In this paper, we analyze two kinds of location-based patterns. The first is the association between location attributes and the locations of user tweets. The second is location association pattern which comprises a pair of locations that are co-visited by users. We demonstrate that through tracking the Twitter data of Singapore-based users, we are able to reveal association between users tweeting from school locations and the school type as well as the competitiveness of schools. We also discover location association patterns which involve schools and shopping malls. With these location-based patterns offering interesting insights about the visit behaviors of school and shopping mall users, we further develop an online visual application called Urbanatics to explore the location association patterns making use of both chord diagram and map visualization.