We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purchase suggestions. Existing approaches typically learn from behavior-derived item-item associations using GNNs or leverage item content alone. However, these methods often overlook two key challenges: (i) user behaviors (e.g., co-view/co-purchase) only provide noisy weak supervision, and (ii) behavior signals are long-tailed, leaving many items with sparse associations. We propose MMSC, a self-supervised multi-modal relational representation learning framework that combines a multi-modal foundation model adapted to encode item metadata and a self-supervised denoising module that learns relationship-aware representations from noisy user behaviors, unified by a hierarchical aggregation mechanism. We further use LLM-assisted supervision to mitigate noise in behavior-derived supervision during training. Experiments on five real-world datasets show that MMSC consistently outperforms existing baselines by 26.1% for substitutable and 39.2% for complementary item inference, while remaining effective for cold-start items.

This paper proposes a novel pre-trained framework for zero-shot cross-domain sequential recommendation without auxiliary information. While using auxiliary information (e.g., item descriptions) seems promising for cross-domain transfer, a cross-domain adaptation of sequential recommenders can be challenging when the target domain differs from the source domain—item descriptions are in different languages; metadata modalities (e.g., audio, image, and text) differ across source and target domains. If we can learn universal item representations independent of the domain type (e.g., groceries, movies), we can achieve zero-shot cross-domain transfer without auxiliary information. Our critical insight is that user interaction sequences highlight shifting user preferences via the popularity dynamics of interacted items. We present a pre-trained sequential recommendation framework: PrepRec, which utilizes a novel popularity dynamics-aware transformer architecture. Through extensive experiments on five real-world datasets, we show that PrepRec, without any auxiliary information, can zero-shot adapt to new application domains and achieve competitive performance compared to state-of-the-art sequential recommender models. In addition, we show that PrepRec complements existing sequential recommenders. With a simple post-hoc interpolation, PrepRec improves the performance of existing sequential recommenders on average by 11.8% in Recall@10 and 22% in NDCG@10. We provide an anonymized implementation of PrepRec at https://github.com/CrowdDynamicsLab/preprec.

In recent times, deep learning methods have supplanted conventional collaborative filtering approaches as the backbone of modern recommender systems. However, their gains are skewed towards popular items with a drastic performance drop for the vast collection of long-tail items with sparse interactions. Moreover, we empirically show that prior neural recommenders lack the resolution power to accurately rank relevant items within the long-tail.

The quality variance in user-generated content is a major bottleneck to serving communities on online platforms. Current content ranking methods primarily evaluate text and non-textual content features of each user post in isolation. In this paper, we demonstrate the utility of considering the implicit and explicit relational aspects across user content to assess their quality. First, we develop a modular platform-agnostic framework to represent the contrastive (or competing) and similarity-based relational aspects of user-generated content via independently induced content graphs. Second, we develop two complementary graph convolutional operators that enable feature contrast for competing content and feature smoothing/sharing for similar content. Depending on the edge semantics of each content graph, we embed its nodes via one of the above two mechanisms. We also show that our contrastive operator creates discriminative magnification across the embeddings of competing posts. Third, we show a surprising result-applying classical boosting techniques to combine final-layer embeddings across the content graphs significantly outperforms the typical stacking, fusion, or neighborhood embedding aggregation methods in graph convolutional architectures. We exhaustively validate our method via accepted answer prediction over fifty diverse Stack-Exchange (https://stackexchange.com/) websites with consistent relative gains of over 5% accuracy over state-of-the-art neural, multi-relational and textual baselines.

This article introduces a novel task-independent sampler for attributed networks. The problem is important because while data mining tasks on network content are common, sampling on internet-scale networks is costly. Link-trace samplers such as Snowball sampling, Forest Fire, Random Walk, and Metropolis–Hastings Random Walk are widely used for sampling from networks. The design of these attribute-agnostic samplers focuses on preserving salient properties of network structure, and are not optimized for tasks on node content. This article has three contributions. First, we propose a task-independent, attribute aware link-trace sampler grounded in Information Theory. Our sampler greedily adds to the sample the node with the most informative (i.e., surprising) neighborhood. The sampler tends to rapidly explore the attribute space, maximally reducing the surprise of unseen nodes. Second, we prove that content sampling is an NP-hard problem. A well-known algorithm best approximates the optimization solution within 1 − 1/ e , but requires full access to the entire graph. Third, we show through empirical counterfactual analysis that in many real-world datasets, network structure does not hinder the performance of surprise based link-trace samplers. Experimental results over 18 real-world datasets reveal: surprise-based samplers are sample efficient and outperform the state-of-the-art attribute-agnostic samplers by a wide margin (e.g., 45% performance improvement in clustering tasks).

We present InfoMotif, a new semi-supervised, motif-regularized, learning framework over graphs. We overcome two key limitations of message passing in popular graph neural networks (GNNs): localization (a k-layer GNN cannot utilize features outside the k-hop neighborhood of the labeled training nodes) and over-smoothed (structurally indistinguishable) representations. We propose the concept of attributed structural roles of nodes based on their occurrence in different network motifs, independent of network proximity. Two nodes share attributed structural roles if they participate in topologically similar motif instances over co-varying sets of attributes. Further, InfoMotif achieves architecture independence by regularizing the node representations of arbitrary GNNs via mutual information maximization. Our training curriculum dynamically prioritizes multiple motifs in the learning process without relying on distributional assumptions in the underlying graph or the learning task. We integrate three state-of-the-art GNNs in our framework, to show significant gains (3-10% accuracy) across six diverse, real-world datasets. We see stronger gains for nodes with sparse training labels and diverse attributes in local neighborhood structures.

The rapid proliferation of new users and items on the social web has aggravated the gray-sheep user/long-tail item challenge in recommender systems. Historically, cross-domain co-clustering methods have successfully leveraged shared users and items across dense and sparse domains to improve inference quality. However, they rely on shared rating data and cannot scale to multiple sparse target domains (i.e., the one-to-many transfer setting). This, combined with the increasing adoption of neural recommender architectures, motivates us to develop scalable neural layer-transfer approaches for cross-domain learning. Our key intuition is to guide neural collaborative filtering with domain-invariant components shared across the dense and sparse domains, improving the user and item representations learned in the sparse domains. We leverage contextual invariances across domains to develop these shared modules, and demonstrate that with user-item interaction context, we can learn-to-learn informative representation spaces even with sparse interaction data. We show the effectiveness and scalability of our approach on two public datasets and a massive transaction dataset from Visa, a global payments technology company (19% Item Recall, 3x faster vs. training separate models for each domain). Our approach is applicable to both implicit and explicit feedback settings.

We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together. Existing studies target persistent groups with substantial activity history, while ephemeral groups lack historical interactions. To overcome group interaction sparsity, we propose data-driven regularization strategies to exploit both the preference covariance amongst users who are in the same group, as well as the contextual relevance of users' individual preferences to each group.

Some social networks provide explicit mechanisms to allocate social rewards such as reputation based on users’ actions, while the mechanism is more opaque in other networks. Nonetheless, there are always individuals who obtain greater rewards and reputation than their peers. An intuitive yet important question to ask is whether these successful users employ strategic behaviors to become influential. It might appear that the influencers ”have gamed the system.” However, it remains difficult to conclude the rationality of their actions due to factors like the combinatorial strategy space, inability to determine payoffs, and resource limitations faced by individuals. The challenging nature of this question has drawn attention from both the theory and data mining communities. Therefore, in this paper, we are motivated to investigate if resource-limited individuals discover strategic behaviors associated with high payoffs when producing collaborative/interactive content in social networks. We propose a novel framework of Dynamic Dual Attention Networks (DDAN) which models individuals’ content production strategies through a generative process, under the influence of social interactions involved in the process. Extensive experimental results illustrate the model’s effectiveness in user behavior modeling. We make three strong empirical findings: (1) Different strategies give rise to different social payoffs; (2) The best performing individuals exhibit stability in their preference over the discovered strategies, which indicates the emergence of strategic behavior; and (3) The stability of a user’s preference is correlated with high payoffs.

This paper proposes a novel algorithm to discover hidden individuals in a social network. The problem is increasingly important for social scientists as the populations (e.g., individuals with mental illness) that they study converse online. Since these populations do not use the category (e.g., mental illness) to self-describe, directly querying with text is non-trivial. To by-pass the limitations of network and query re-writing frameworks, we focus on identifying hidden populations through attributed search. We propose a hierarchical Multi-Arm Bandit (DT-TMP) sampler that uses a decision tree coupled with reinforcement learning to query the combinatorial attributed search space by exploring and expanding along high yielding decision-tree branches. A comprehensive set of experiments over a suite of twelve sampling tasks on three online web platforms, and three offline entity datasets reveals that DT-TMP outperforms all baseline samplers by upto a margin of 54% on Twitter and 48% on RateMDs. An extensive ablation study confirms DT-TMP's superior performance under different sampling scenarios.

This paper proposes a novel framework to incorporate social regularization for item recommendation. Social regularization grounded in ideas of homophily and influence appears to capture latent user preferences. However, there are two key challenges: first, the importance of a specific social link depends on the context and second, a fundamental result states that we cannot disentangle homophily and influence from observational data to determine the effect of social inference. Thus we view the attribution problem as inherently adversarial where we examine two competing hypothesis---social influence and latent interests---to explain each purchase decision. We make two contributions. First, we propose a modular, adversarial framework that decouples the architectural choices for the recommender and social representation models, for social regularization. Second, we overcome degenerate solutions through an intuitive contextual weighting strategy, that supports an expressive attribution, to ensure informative social associations play a larger role in regularizing the learned user interest space. Our results indicate significant gains (5-10% relative [email protected]) over state-of-the-art baselines across multiple publicly available datasets.

This paper proposes an attributed network growth model. Despite the knowledge that individuals use limited resources to form connections to similar others, we lack an understanding of how local and resource-constrained mechanisms explain the emergence of structural properties found in real-world networks. We make three contributions. First, we propose a simple and accurate model of attributed network growth that jointly explains the emergence of in-degree, local clustering, clustering-degree relationship and attribute mixing patterns. Second, we make use of biased random walks to develop a model that forms edges locally, without recourse to global information. Third, we account for multiple sociological phenomena: bounded rationality; structural constraints; triadic closure; attribute homophily; preferential attachment. Our experiments show that the proposed Attributed Random Walk (ARW) model accurately preserves network structure and attribute mixing patterns of real-world networks; it improves upon the performance of eight well-known models by a significant margin of 2.5-10 × .

This paper proposes an approach to learn robust behavior representations in online platforms by addressing the challenges of user behavior skew and sparse participation. Latent behavior models are important in a wide variety of applications: recommender systems; prediction; user profiling; community characterization. Our framework is the first to jointly address skew and sparsity across graphical behavior models. We propose a generalizable bayesian approach to partition users in the presence of skew while simultaneously learning latent behavior profiles over these partitions to address user-level sparsity. Our behavior profiles incorporate the temporal activity and links between participants, although the proposed framework is flexible to introduce other definitions of participant behavior. Our approach explicitly discounts frequent behaviors and learns variable size partitions capturing diverse behavior trends. The partitioning approach is data-driven with no rigid assumptions, adapting to varying degrees of skew and sparsity.

In recent times, deep neural networks have found success in Collaborative Filtering (CF) based recommendation tasks. By parametrizing latent factor interactions of users and items with neural architectures, they achieve significant gains in scalability and performance over matrix factorization. However, the long-tail phenomenon in recommender performance persists on the massive inventories of online media or retail platforms. Given the diversity of neural architectures and applications, there is a need to develop a generalizable and principled strategy to enhance long-tail item coverage.

In this paper, we interpret the community question answering websites on the StackExchange platform as knowledge markets, and analyze how and why these markets can fail at scale. A knowledge market framing allows site operators to reason about market failures, and to design policies to prevent them. Our goal is to provide insights on large-scale knowledge market failures through an interpretable model. We explore a set of interpretable economic production models on a large empirical dataset to analyze the dynamics of content generation in knowledge markets. Amongst these, the Cobb-Douglas model best explains empirical data and provides an intuitive explanation for content generation through the concepts of elasticity and diminishing returns. Content generation depends on user participation and also on how specific types of content (e.g. answers) depends on other types (e.g. questions). We show that these factors of content generation have constant elasticity and a percentage increase in any of the inputs leads to a constant percentage increase in the output. Furthermore, markets exhibit diminishing returns-the marginal output decreases as the input is incrementally increased. Knowledge markets also vary on their returns to scale-the increase in output resulting from a proportionate increase in all inputs. Importantly, many knowledge markets exhibit diseconomies of scale-measures of market health (e.g., the percentage of questions with an accepted answer) decrease as a function of the number of participants. The implications of our work are two-fold: site operators ought to design incentives as a function of system size (number of participants); the market lens should shed insight into complex dependencies amongst different content types and participant actions in general social networks.

This work aims at discovering community structure in rich media social networks through analysis of time-varying, multirelational data. Community structure represents the latent social context of user actions. It has important applications such as search and recommendation. The problem is particularly useful in the enterprise domain, where extracting emergent community structure on enterprise social media can help in forming new collaborative teams, in expertise discovery, and in the long term reorganization of enterprises based on collaboration patterns. There are several unique challenges: (a) In social media, the context of user actions is constantly changing and coevolving; hence the social context contains time-evolving multidimensional relations. (b) The social context is determined by the available system features and is unique in each social media platform; hence the analysis of such data needs to flexibly incorporate various system features. In this article we propose MetaFac (MetaGraph Factorization), a framework that extracts community structures from dynamic, multidimensional social contexts and interactions. Our work has three key contributions: (1) metagraph, a novel relational hypergraph representation for modeling multirelational and multidimensional social data; (2) an efficient multirelational factorization method for community extraction on a given metagraph; (3) an online method to handle time-varying relations through incremental metagraph factorization. Extensive experiments on real-world social data collected from an enterprise and the public Digg social media Web site suggest that our technique is scalable and is able to extract meaningful communities from social media contexts. We illustrate the usefulness of our framework through two prediction tasks: (1) in the enterprise dataset, the task is to predict users’ future interests on tag usage, and (2) in the Digg dataset, the task is to predict users’ future interests in voting and commenting on Digg stories. Our prediction significantly outperforms baseline methods (including aspect model and tensor analysis), indicating the promising direction of using metagraphs for handling time-varying social relational contexts.

This article analyzes communication within a set of individuals to extract the representative prototypical groups and provides a novel framework to establish the utility of such groups. Corporations may want to identify representative groups (which are indicative of the overall communication set) because it is easier to track the prototypical groups rather than the entire set. This can be useful for advertising, identifying “hot” spots of resource consumption as well as in mining representative moods or temperature of a community. Our framework has three parts: extraction, characterization, and utility of prototypical groups. First, we extract groups by developing features representing communication dynamics of the individuals. Second, to characterize the overall communication set, we identify a subset of groups within the community as the prototypical groups. Third, we justify the utility of these prototypical groups by using them as predictors of related external phenomena; specifically, stock market movement of technology companies and political polls of Presidential candidates in the 2008 U.S. elections. We have conducted extensive experiments on two popular blogs, Engadget and Huffington Post. We observe that the prototypical groups can predict stock market movement/political polls satisfactorily with mean error rate of 20.32%. Further, our method outperforms baseline methods based on alternative group extraction and prototypical group identification methods. We evaluate the quality of the extracted groups based on their conductance and coverage measures and develop metrics: predictivity and resilience to evaluate their ability to predict a related external time-series variable (stock market movement/political polls). This implies that communication dynamics of individuals are essential in extracting groups in a community, and the prototypical groups extracted by our method are meaningful in characterizing the overall communication sets.

In this paper, we introduce AURA, a novel framework for enriching the physical environment with information about objects and activities in order to support searches in the physical world. The goal is to enable individuals to use the environment in which they function as a living (short-term) memory of their activities and of the objects with which they interact in this environment. In order to act as a memory, the physical environment must be transparently embedded with relevant information and made accessible by in-situ search mechanisms. We achieve this embedding through innovative algorithms that leverage a collection of parasitic RFID tags distributed in the environment to act as a distributed storage cloud. Information about the activities of the users and objects with which they interact are encoded and stored, in a decentralized way, on these RFID tags to support attribute-based search. A novel auraProp algorithm disseminates information in the environment and a complementary auraSearch algorithm implements spatial searches for physical objects in the environment. Parasitic RFID tags are not self-powered and thus cannot communicate among each other. AURA leverages human movement in the environment to propagate information: as they move in the environment, users not only leave traces (or auras) of their own activities, but also help further disseminate auras of prior activities in the same space. AURA relies on a novel signature based information dissemination mechanism and a randomized information erasure scheme to ensure that the extremely limited storage spaces available on the RFID tags are used effectively. The erasure scheme also helps create an information gradient in the physical environment, which the auraSearch algorithm uses to direct the user towards the object of interest.

This paper aims at discovering community structure in rich media social networks, through analysis of time-varying, multi-relational data. Community structure represents the latent social context of user actions. It has important applications in information tasks such as search and recommendation. Social media has several unique challenges. (a) In social media, the context of user actions is constantly changing and co-evolving; hence the social context contains time-evolving multi-dimensional relations. (b) The social context is determined by the available system features and is unique in each social media website. In this paper we propose MetaFac (MetaGraph Factorization), a framework that extracts community structures from various social contexts and interactions. Our work has three key contributions: (1) metagraph, a novel relational hypergraph representation for modeling multi-relational and multi-dimensional social data; (2) an efficient factorization method for community extraction on a given metagraph; (3) an on-line method to handle time-varying relations through incremental metagraph factorization. Extensive experiments on real-world social data collected from the Digg social media website suggest that our technique is scalable and is able to extract meaningful communities based on the social media contexts. We illustrate the usefulness of our framework through prediction tasks. We outperform baseline methods (including aspect model and tensor analysis) by an order of magnitude.

The tasks in the physical environments are mainly information centric processes, such as search and exploration of physical objects. We have developed an informational environment, AURA that supports object searches in the physical world. The goal of AURA is to enable individuals to use the environment in which they function as a living (short-term) memory of their activities and of the objects with which they interact in this environment. To support physical searches, the environment that the user is occupying must be transparently embedded with relevant information and made accessible by in-situ search mechanisms. We achieve this through innovative algorithms that re-imagine a collection of environmentally distributed RFID tags to act as a distributed storage cloud that encodes the required information for attribute-based object search. Since RFID tags lack radio transmitters and, thus, cannot communicate among each other, auraProp and auraSearch leverage the movements of the humans in the environment to propagate information: as they move in the environment, users not only leave traces (or auras) of their own activities, but also help further disseminate auras of prior activities in the same space. This scheme creates an information-gradient in the physical environment which AURA then leverages to direct the user toward the object of interest. auraSearch significantly reduces the number of steps that the user has to walk while searching for a given object.

Rich media social networks promote not only creation and consumption of media, but also communication about the posted media item. What causes a conversation to be interesting, that prompts a user to participate in the discussion on a posted video? We conjecture that people participate in conversations when they find the conversation theme interesting, see comments by people whom they are familiar with, or observe an engaging dialogue between two or more people (absorbing back and forth exchange of comments). Importantly, a conversation that is interesting must be consequential - i.e. it must impact the social network itself.

Social media websites promote diverse user interaction on media objects as well as user actions with respect to other users. The goal of this work is to discover community structure in rich media social networks, and observe how it evolves over time, through analysis of multi-relational data. The problem is important in the enterprise domain where extracting emergent community structure on enterprise social media, can help in forming new collaborative teams, aid in expertise discovery, and guide long term enterprise reorganization. Our approach consists of three main parts: (1) a relational hypergraph model for modeling various social context and interactions; (2) a novel hypergraph factorization method for community extraction on multi-relational social data; (3) an on-line method to handle temporal evolution through incremental hypergraph factorization. Extensive experiments on real-world enterprise data suggest that our technique is scalable and can extract meaningful communities. To evaluate the quality of our mining results, we use our method to predict users' future interests. Our prediction outperforms baseline methods (frequency counts, pLSA) by 36-250% on the average, indicating the utility of leveraging multi-relational social context by using our method.

We discover communities from social network data and analyze the community evolution. These communities are inherent characteristics of human interaction in online social networks, as well as paper citation networks. Also, communities may evolve over time, due to changes to individuals' roles and social status in the network as well as changes to individuals' research interests. We present an innovative algorithm that deviates from the traditional two-step approach to analyze community evolutions. In the traditional approach, communities are first detected for each time slice, and then compared to determine correspondences. We argue that this approach is inappropriate in applications with noisy data. In this paper, we propose FacetNet for analyzing communities and their evolutions through a robust unified process. This novel framework will discover communities and capture their evolution with temporal smoothness given by historic community structures. Our approach relies on formulating the problem in terms of maximum a posteriori (MAP) estimation, where the community structure is estimated both by the observed networked data and by the prior distribution given by historic community structures. Then we develop an iterative algorithm, with proven low time complexity, which is guaranteed to converge to an optimal solution. We perform extensive experimental studies, on both synthetic datasets and real datasets, to demonstrate that our method discovers meaningful communities and provides additional insights not directly obtainable from traditional methods.

We have developed a computational framework to characterize social network dynamics in the blogosphere at individual, group and community levels. Such characterization could be used by corporations to help drive targeted advertising and to track the moods and sentiments of consumers. We tested our model on a widely read technology blog called Engadget. Our results show that communities transit between states of high and low entropy, depending on sentiments (positive / negative) about external happenings. We also propose an innovative method to establish the utility of the extracted knowledge, by correlating the mined knowledge with an external time series data (the stock market). Our validation results show that the characterized groups exhibit high stock market movement predictability (89%) and removal of 'impactful' groups makes the community less resilient by lowering predictability (26%) and affecting the composition of the groups in the rest of the community.

We present a framework for automatically summarizing social group activity over time. The problem is important in understanding large scale online social networks, which have diverse social interactions and exhibit temporal dynamics. In this work we construct summarization by extracting activity themes. We propose a novel unified temporal multi-graph framework for extracting activity themes over time. We use non-negative matrix factorization (NMF) approach to derive two interrelated latent spaces for users and concepts. Activity themes are extracted from the derived latent spaces to construct group activity summary. Experiments on real-world Flickr datasets demonstrate that our technique outperforms baseline algorithms such as LSI, and is additionally able to extract temporally representative activities to construct meaningful group activity summary.

We discover communities from social network data, and analyze the community evolution. These communities are inherent characteristics of human interaction in online social networks, as well as paper citation networks. Also, communities may evolve over time, due to changes to individuals' roles and social status in the network as well as changes to individuals' research interests. We present an innovative algorithm that deviates from the traditional two-step approach to analyze community evolutions. In the traditional approach, communities are first detected for each time slice, and then compared to determine correspondences. We argue that this approach is inappropriate in applications with noisy data. In this paper, we propose FacetNet for analyzing communities and their evolutions through a robust unified process. In this novel framework, communities not only generate evolutions, they also are regularized by the temporal smoothness of evolutions. As a result, this framework will discover communities that jointly maximize the fit to the observed data and the temporal evolution. Our approach relies on formulating the problem in terms of non-negative matrix factorization, where communities and their evolutions are factorized in a unified way. Then we develop an iterative algorithm, with proven low time complexity, which is guaranteed to converge to an optimal solution. We perform extensive experimental studies, on both synthetic datasets and real datasets, to demonstrate that our method discovers meaningful communities and provides additional insights not directly obtainable from traditional methods.

This article addresses the problem of spam blog (splog) detection using temporal and structural regularity of content, post time and links. Splogs are undesirable blogs meant to attract search engine traffic, used solely for promoting affiliate sites. Blogs represent popular online media, and splogs not only degrade the quality of search engine results, but also waste network resources. The splog detection problem is made difficult due to the lack of stable content descriptors. We have developed a new technique for detecting splogs, based on the observation that a blog is a dynamic, growing sequence of entries (or posts) rather than a collection of individual pages. In our approach, splogs are recognized by their temporal characteristics and content. There are three key ideas in our splog detection framework. (a) We represent the blog temporal dynamics using self-similarity matrices defined on the histogram intersection similarity measure of the time, content, and link attributes of posts, to investigate the temporal changes of the post sequence. (b) We study the blog temporal characteristics using a visual representation derived from the self-similarity measures. The visual signature reveals correlation between attributes and posts, depending on the type of blogs (normal blogs and splogs). (c) We propose two types of novel temporal features to capture the splog temporal characteristics. In our splog detector, these novel features are combined with content based features. We extract a content based feature vector from blog home pages as well as from different parts of the blog. The dimensionality of the feature vector is reduced by Fisher linear discriminant analysis. We have tested an SVM-based splog detector using proposed features on real world datasets, with appreciable results (90% accuracy).

The paper develops a novel computational framework for predicting communication flow in social networks based on several contextual features. The problem is important because prediction of communication flow can impact timely sharing of specific information across a wide array of communities. We determine the intent to communicate and communication delay between users based on several contextual features in a social network corresponding to (a) neighborhood context, (b) topic context and (c) recipient context. The intent to communicate and communication delay are modeled as regression problems which are efficiently estimated using Support Vector Regression. We predict the intent and the delay, on an interval of time using past communication data. We have excellent prediction results on a real-world dataset from MySpace.com with an accuracy of 13-16%. We show that the intent to communicate is more significantly influenced by contextual factors compared to the delay.

There are information needs involving costly decisions that cannot be efficiently satisfied through conventional Web search engines. Alternately, community centric search can provide multiple viewpoints to facilitate decision making. We propose to discover and model the temporal dynamics of thematic communities based on mutual awareness, where the awareness arises due to observable blogger actions and the expansion of mutual awareness leads to community formation. Given a query, we construct a directed action graph that is time-dependent, and weighted with respect to the query. We model the process of mutual awareness expansion using a random walk process and extract communities based on the model. We propose an interaction space based representation to quantify community dynamics. Each community is represented as a vector in the interaction space and its evolution is determined by a novel interaction correlation method. We have conducted experiments with a real-world blog dataset and have promising results for detection as well as insightful results for community evolution.