Kuntal Dey

Large maximal cliques enumeration in sparse graphs

Here we study a variant of maximal clique enumeration problem by incorporating a minimum size criterion. We describe preprocessing techniques to reduce the graph size. This is of practical interest since enumerating maximal cliques is a computationally hard problem and the execution time increases rapidly with the input size. We discuss basics of an algorithm for enumerating large maximal cliques which exploits the constraint on minimum size of the desired maximal cliques. Social networks are prime examples of large sparse graphs where enumerating large maximal cliques is of interest. We present experimental results on the social network formed by the call detail records of one of the worlds largest telecom service providers. Our results show that the preprocessing methods achieve significant reduction in the graph size. We also characterize the execution behaviour of our large maximal clique enumeration algorithm.

Discovery and analysis of evolving topical social discussions on unstructured microblogs

Social networks have emerged as hubs of user generated content. Online social conversations can be used to retrieve users interests towards given topics and trends. Microblogging platforms like Twitter are primary examples of social networks with significant volumes of topical message exchanges between users. However, unlike traditional online discussion forums, blogs and social networking sites, explicit discussion threads are absent from microblogging networks like Twitter. This inherent absence of any conversation framework makes it challenging to distinguish conversations from mere topical interests. In this work, we explore semantic, social and temporal relationships of topical clusters formed in Twitter to identify conversations. We devise an algorithm comprising of a sequence of steps such as text clustering, topical similarity detection using TF-IDF and Wordnet, and intersecting social, semantic and temporal graphs to discover social conversations around topics. We further qualitatively show the presence of social localization of discussion threads. Our results suggest that discussion threads evolve significantly over social networks on Twitter. Our algorithm to find social discussion threads can be used for settings such as social information spreading applications and information diffusion analyses on microblog networks.

Like-minded communities: bringing the familiarity and similarity together

Community detection in social networks is a well-studied problem. A community in social network is commonly defined as a group of people whose interactions within the group are more than outside the group. It is believed that people’s behavior can be linked to the behavior of their social neighborhood. While shared characteristics of communities have been used to validate the communities found, to the best of authors’ knowledge, it is not demonstrated in the literature that communities found using social interaction data are like-minded, i.e., they behave similarly in terms of their interest in items (e.g., movie, products). In this paper, we experimentally demonstrate, on a social networking movie rating dataset, that people who are interested in an item are socially better connected than the overall graph. Motivated by this fact, we propose a method for finding communities wherein like-mindedness is an explicit objective. We find small tight groups with many shared interests using a frequent item set mining approach and use these as building blocks for the core of these like-minded communities. We show that these communities have higher similarity in their interests compared to communities found using only the interaction information. We also compare our method against a baseline where the weight of edges are defined based on similarity in interests between nodes and show that our approach achieves far higher level of like-mindedness amongst the communities compared to this baseline as well.

Leveraging social networks for corporate staffing and expert recommendation

Effective management of human resources is a significant challenge faced by most organizations. In this paper, we look at two problems that arise in large, globally distributed organizations: staffing projects with the required subject matter experts and connecting subject matter experts to other employees who can benefit from their expertise. Several approaches based on automated skill matching have been suggested in the past to solve these problems. However, we argue that social relationships play an important role in both of these functions, and better matches can be obtained by combining skill matching with rich social interaction data. We describe two systems that exploit social networking data to solve these problems and report the results of real life experiments performed using these systems.

Eye center localization and detection using radial mapping

We propose a geometrical method, applied over eye-specific features, to improve the accuracy of the art of eye-center localization. Our solution is built upon: (a) checking radially constrained gradient vectors, (b) adding weightage to iris specific features and (c) considering bi-directional image gradients to eliminate errors due to reflection on pupil. Our system outperforms the state of the art methods, when compared collectively across multiple benchmark databases, such as BioID and FERET. Our process is lightweight, robust and significantly fast: achieving 50-60 fps for eye center localization, using a single threaded approach on a 2.4 GHz CPU with no GPU. This makes it practicable for real-life applications.

ISURE: User authentication in mobile devices using ocular biometrics in visible spectrum

In this paper, we propose a supervised learning based model for ocular biometrics. Using Speeded-Up Robust Features (SURF) for detecting local features of the eye region, we create a local feature descriptor vector of each image. We cluster these feature vectors, representing an image as a normalized histogram of membership to various clusters, thereby creating a bag-of-visual-words model. We conduct a multiphase training, first performing a fast Multinomial Naïve Bayes learning, and subsequently using a pyramid-up topology to use the top k% results (based upon confidence scores) thus predicted and perform Dense SIFT for nearest neighbor matching. Contrary to traditional ocular biometric systems, our proposed approach does not rely highly accurate iris pattern segmentation, allowing less constrained image acquisition conditions such as from mobile devices. Our method identifies the individuals with an identification accuracy varying from 48.76% to 79.49%, across different lighting conditions and phone handset data sources, while testing on the given data.

CDR Analysis Based Telco Churn Prediction and Customer Behavior Insights: A Case Study

Telecom churn has emerged as the single largest cause of revenue erosion for telecom operators. Predicting churners from the demographic and behavioral information of customers has been a topic of active research interest and industrial practice. In this case study paper, we present our experience of participating in a competitive evaluation for churn prediction and customer insights for a leading Asian telecom operator. We build a data mining model to predict churners using key performance indicators (KPI) based on customer Call Detail Records (CDR) and additional customer data available with the operator. Further, we analyze the social network formed between the (prepaid and postpaid) churners as well as the entire subscriber base. Our churn prediction method provided a lift of 8.4 over a nominal churn rate of 4.17% on 10% of the prepaid talking subscriber base on test data, and a lift of 7.62 on a nominal churn rate of 7.3% as reported in the customer evaluation on unseen data. This outperformed next best competitor in the study by more than twice. We also correlate social behavior patterns for churners and overall subscriber base. Our study indicates strong socially influenced churn among postpaid subscribers, in contrast with the prepaid subscribers. Our work provides guidelines and a template for conducting similar real-world studies for large telecom operators.

Discovery and analysis of tightly knit communities in telecom social networks

Community identif ication has been a major research area in social network analysis. One popular type of community is one in which every member of the community knows every other member, which can be viewed as a clique in a graph representing the social network. In this paper, we present a novel highly scalable method for finding large maximal cliques that is validated with experimental results on several real-life social networks. In addition, while the importance of finding tightly knit communities has been widely accepted, the influence of community on the behavior of the individuals belonging to those communities is relatively unexplored. We also attempt to answer various questions in the context of cliques as communities in telecom social networks: how individuals in communities behave, what influence a community has on the behavior of an individual, and whether communities have a characteristic behavior of their own. We also examine whether the behavior of individuals who belong to communities differs from those who do not. We believe that the findings of such a study will reassert the importance of finding communities in telecom social networks and will help telecom operators improve group targeting and customer relationship management.

Leveraging Cognitive Features for Sentiment Analysis.

Sentiments expressed in user-generated short text and sentences are nuanced by subtleties at lexical, syntactic, semantic and pragmatic levels. To address this, we propose to augment traditional features used for sentiment analysis and sarcasm detection, with cognitive features derived from the eye-movement patterns of readers. Statistical classification using our enhanced feature set improves the performance (F-score) of polarity detection by a maximum of 3.7% and 9.3% on two datasets, over the systems that use only traditional features. We perform feature significance analysis, and experiment on a held-out dataset, showing that cognitive features indeed empower sentiment analyzers to handle complex constructs.

Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification using Convolutional Neural Network

Cognitive NLP systems- i.e., NLP systems that make use of behavioral data - augment traditional text-based features with cognitive features extracted from eye-movement patterns, EEG signals, brain-imaging etc. Such extraction of features is typically manual. We contend that manual extraction of features may not be the best way to tackle text subtleties that characteristically prevail in complex classification tasks like Sentiment Analysis and Sarcasm Detection, and that even the extraction and choice of features should be delegated to the learning system. We introduce a framework to automatically extract cognitive features from the eye-movement/gaze data of human readers reading the text and use them as features along with textual features for the tasks of sentiment polarity and sarcasm detection. Our proposed framework is based on Convolutional Neural Network (CNN). The CNN learns features from both gaze and text and uses them to classify the input text. We test our technique on published sentiment and sarcasm labeled datasets, enriched with gaze information, to show that using a combination of automatically learned text and gaze features often yields better classification performance over (i) CNN based systems that rely on text input alone and (ii) existing systems that rely on handcrafted gaze and textual features.