Ayan Bhowmick

arXiv (Cornell University), Feb 26, 2024

Dialog summarization has become increasingly important in managing and comprehending large-scale ... more Dialog summarization has become increasingly important in managing and comprehending large-scale conversations across various domains. This task presents unique challenges in capturing the key points, context, and nuances of multi-turn long conversations for summarization. It is worth noting that the summarization techniques may vary based on specific requirements such as in a shopping-chatbot scenario, the dialog summary helps to learn user preferences, whereas in the case of a customer call center, the summary may involve the problem attributes that a user specified, and the final resolution provided. This work emphasizes the significance of creating coherent and contextually rich summaries for effective communication in various applications. We explore current state-of-the-art approaches for long dialog summarization in different domains and benchmark metrics based evaluations show that one single model does not perform well across various areas for distinct summarization tasks.

Download

Automating question generation from educational text

arXiv (Cornell University), Sep 25, 2023

The use of question-based activities (QBAs) is wide-spread in education, traditionally forming an... more The use of question-based activities (QBAs) is wide-spread in education, traditionally forming an integral part of the learning and assessment process. In this paper, we design and evaluate an automated question generation tool for formative and summative assessment in schools. We present an expert survey of one hundred and four teachers, demonstrating the need for automated generation of QBAs, as a tool that can significantly reduce the workload of teachers and facilitate personalized learning experiences. Leveraging the recent advancements in generative AI, we then present a modular framework employing transformer based language models for automatic generation of multiple-choice questions (MCQs) from textual content. The presented solution, with distinct modules for question generation, correct answer prediction, and distractor formulation, enables us to evaluate different language models and generation techniques. Finally, we perform an extensive quantitative and qualitative evaluation, demonstrating trade-offs in the use of different techniques and models.

Download

On the Network Embedding in Sparse Signed Networks

Lecture Notes in Computer Science, 2019

Network embedding, that learns low-dimensional node representations in a graph such that the netw... more Network embedding, that learns low-dimensional node representations in a graph such that the network structure is preserved, has gained significant attention in recent years. Most state-of-the-art embedding methods have mainly designed algorithms for representing nodes in unsigned social networks. Moreover, recent embedding approaches designed for the sparse real-world signed networks have several limitations, especially in the presence of a vast majority of disconnected node pairs with opposite polarities towards their common neighbors. In this paper, we propose sign2vec, a deep learning based embedding model designed to represent nodes in a sparse signed network. sign2vec leverages on signed random walks to capture the higher-order neighborhood relationships between node pairs, irrespective of their connectivity. We design a suitable objective function to optimize the learned node embeddings such that the link forming behavior of individual nodes is captured. Experiments on empirical signed network datasets demonstrate the effectiveness of embeddings learned by sign2vec for several downstream applications while outperforming state-of-the-art baseline algorithms.

LouvainNE

Network embedding, that aims to learn low-dimensional vector representation of nodes such that th... more Network embedding, that aims to learn low-dimensional vector representation of nodes such that the network structure is preserved, has gained significant research attention in recent years. However, most state-of-the-art network embedding methods are computationally expensive and hence unsuitable for representing nodes in billion-scale networks. In this paper, we present LouvainNE, a hierarchical clustering approach to network embedding. Precisely, we employ Louvain, an extremely fast and accurate community detection method, to build a hierarchy of successively smaller subgraphs. We obtain representations of individual nodes in the original graph at different levels of the hierarchy, then we aggregate these representations to learn the final embedding vectors. Our theoretical analysis shows that our proposed algorithm has quasi-linear runtime and memory complexity. Our extensive experimental evaluation, carried out on multiple real-world networks of different scales, demonstrates both (i) the scalability of our proposed approach that can handle graphs containing tens of billions of edges, as well as (ii) its effectiveness in performing downstream network mining tasks such as network reconstruction and node classification. • Computing methodologies → Machine learning algorithms; • Mathematics of computing → Graph algorithms.

Download

On the Splitting Dynamics of Meetup Social Groups

Proceedings of the International AAAI Conference on Web and Social Media, May 26, 2020

Groups in online social networks witness continuous evolution by loss of existing members and gai... more Groups in online social networks witness continuous evolution by loss of existing members and gain of new members. In this paper, we present a study of group split in Meetup, where a major fraction of members leave the existing group together and join a newly formed group. We identify pivotal group members, called splitters, playing key roles in group split by influencing the existing members to leave the group. We provide an in-depth analysis of the empirical data to reveal key motivating factors leading to a group split and its subsequent impact. Finally, we develop a prediction model for early detection of splitters, as well as the group members likely to be influenced by the splitter to leave the group.

Download

Constructing Influence Trees from Temporal Sequence of Retweets: An Analytical Approach

Twitter is currently a popular microblogging platform for the dissemination of information by use... more Twitter is currently a popular microblogging platform for the dissemination of information by users in the form of messages such as tweets. Such tweets are shared with followers of the seed user who in turn may reshare it with their own set of followers. Long chain of such retweets form cascades. In this paper, we aim to estimate the influence tree of cascades denoting the who-influenced-whom relationship among retweeting users by leveraging on temporal pattern of its retweets. We use a principled methodology to construct the ground truth influence trees of cascades using standard diffusion models. We define diverse structural metrics to quantify the structural characteristics of different influence trees. Based on empirical observations from ground truth, we develop CasCon, an unsupervised model that leverages on temporal pattern of retweets obtained from time series of cascades and underlying follower network of Twitter to construct influence trees. Further, we provide an analytical formulation of CasCon by deriving the degree distribution of these predicted influence trees and use it to approximate the structural metrics. Our evaluation shows that CasCon exhibits superior performance compared to state-of-theart baseline algorithms in selecting influencers of high quality based on standard influence measures in Twitter as well as in correctly (re)constructing the ground truth influence trees with high accuracy. Finally, we validate the analytical formulation of CasCon on the influence tree structures of both synthetic and real cascades; experimental results demonstrate its effectiveness in closely resembling ground truth influence trees for empirical cascades with high retweet count.

Listen to me, my neighbors or my friend? Role of complementary modalities for predicting business popularity in location based social networks

Computer Communications, Feb 1, 2019

Businesses are one of the major stakeholders of the location-based social network (LBSN) platform... more Businesses are one of the major stakeholders of the location-based social network (LBSN) platform. Predicting popularity of businesses in LBSN can help in future business planning and design of effective marketing strategies for business owners. In this paper, we introduce four simple modalities that serve as prime indicators of business popularity, namely, (a) social influence, (b) geographical proximity, (c) customer preference and (d) textual content of tips and reviews posted for a business and investigate their role on business popularity. Characterizing business popularity is ambiguous as there exist different viewpoints to measure popularity. We propose a principled methodology to properly label the popular and unpopular businesses by systematically defining popularity metrics specific to business categories. Social influence essentially represents the peer pressure for visiting certain businesses and eventually contributing to its popularity. Geographical proximity reveals that there are two types of customers visiting a business, namely, local & foreign customers and subsequently, we define the local dominated as well as foreign dominated businesses. On the other hand, customer preference reflects the inclination of a customer towards certain types (say 'Shopping', 'Hotels', 'Religious Organizations', 'Mass Media' etc) of businesses. Further, textual content reveals information about customers' experiences in visiting corresponding businesses. Interestingly, our investigation reveals that customers visit popular businesses amidst social pressure, however they visit unpopular businesses driven by their own personal preference. Moreover, we observe that local (foreign) customers play a major role in shaping the popularity of businesses in local (foreign, respectively) dominated cities. In addition, we observe that textual content of tips and reviews play a significant role in attracting customers to a business adding to its popularity. In a nutshell, this paper puts forward an important message that social influence, geographical proximity, customer preference and textual content exhibit strong complementary signals to predict business popularity. We evaluate the predictive power

Download

On the Splitting Dynamics of Meetup Social Groups

Proceedings of the International AAAI Conference on Web and Social Media

Groups in online social networks witness continuous evolution by loss of existing members and gai... more Groups in online social networks witness continuous evolution by loss of existing members and gain of new members. In this paper, we present a study of group split in Meetup, where a major fraction of members leave the existing group together and join a newly formed group. We identify pivotal group members, called splitters, playing key roles in group split by influencing the existing members to leave the group. We provide an in-depth analysis of the empirical data to reveal key motivating factors leading to a group split and its subsequent impact. Finally, we develop a prediction model for early detection of splitters, as well as the group members likely to be influenced by the splitter to leave the group.

Download

On the Role of Micro-categories to Characterize Event Popularity in Meetup

Proceedings of the International AAAI Conference on Web and Social Media

Event-based social networking platforms such as Meetup have recently witnessed a huge growth. How... more Event-based social networking platforms such as Meetup have recently witnessed a huge growth. However, with the rise in the volume of groups and events, making individual events attractive has become increasingly challenging for its organizers. As a result, we find that events hosted by groups of same category at similar venues and similar times, also widely differ in their popularity. Data study reveals that the topics specified in textual descriptions of events may be key to their popularity. In this paper, we introduce a novel concept of topical micro-categories in the context of EBSNs for accurately characterizing events, such that events belonging to the same micro-category exhibit similar popularity profile. We develop a principled method to detect such micro-categories from the textual descriptions of individual events. Our experiments reveal the significance of the detected micro-categories in determining the popularity of associated Meetup events and groups. We also investi...

Download

On the Network Embedding in Sparse Signed Networks

Advances in Knowledge Discovery and Data Mining, 2019

Network embedding, that learns low-dimensional node representations in a graph such that the netw... more Network embedding, that learns low-dimensional node representations in a graph such that the network structure is preserved, has gained significant attention in recent years. Most state-of-the-art embedding methods have mainly designed algorithms for representing nodes in unsigned social networks. Moreover, recent embedding approaches designed for the sparse real-world signed networks have several limitations, especially in the presence of a vast majority of disconnected node pairs with opposite polarities towards their common neighbors. In this paper, we propose sign2vec, a deep learning based embedding model designed to represent nodes in a sparse signed network. sign2vec leverages on signed random walks to capture the higher-order neighborhood relationships between node pairs, irrespective of their connectivity. We design a suitable objective function to optimize the learned node embeddings such that the link forming behavior of individual nodes is captured. Experiments on empirical signed network datasets demonstrate the effectiveness of embeddings learned by sign2vec for several downstream applications while outperforming state-of-the-art baseline algorithms.

Constructing Influence Trees from Temporal Sequence of Retweets: An Analytical Approach

2018 IEEE International Conference on Big Data (Big Data), 2018

Twitter is currently a popular microblogging platform for the dissemination of information by use... more Twitter is currently a popular microblogging platform for the dissemination of information by users in the form of messages such as tweets. Such tweets are shared with followers of the seed user who in turn may reshare it with their own set of followers. Long chain of such retweets form cascades. In this paper, we aim to estimate the influence tree of cascades denoting the who-influenced-whom relationship among retweeting users by leveraging on temporal pattern of its retweets. We use a principled methodology to construct the ground truth influence trees of cascades using standard diffusion models. We define diverse structural metrics to quantify the structural characteristics of different influence trees. Based on empirical observations from ground truth, we develop CasCon, an unsupervised model that leverages on temporal pattern of retweets obtained from time series of cascades and underlying follower network of Twitter to construct influence trees. Further, we provide an analytical formulation of CasCon by deriving the degree distribution of these predicted influence trees and use it to approximate the structural metrics. Our evaluation shows that CasCon exhibits superior performance compared to state-of-theart baseline algorithms in selecting influencers of high quality based on standard influence measures in Twitter as well as in correctly (re)constructing the ground truth influence trees with high accuracy. Finally, we validate the analytical formulation of CasCon on the influence tree structures of both synthetic and real cascades; experimental results demonstrate its effectiveness in closely resembling ground truth influence trees for empirical cascades with high retweet count.

Temporal Pattern of (Re)tweets Reveal Cascade Migration

Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, 2017

Twitter has recently become one of the most popular online social networking websites where users... more Twitter has recently become one of the most popular online social networking websites where users can share news and ideas through messages in the form of tweets. As a tweet gets retweeted from user to user, large cascades of information diffusion are formed over the global network. Existing works on cascades have mainly focused on predicting their popularity in terms of size. In this paper, we leverage on the temporal pattern of retweets to model the diffusion dynamics of a cascade. Notably, retweet cascades provide two complementary information: (a) inter-retweet time intervals of retweets, and (b) diffusion of cascade over the underlying follower network. Using datasets from Twitter, we identify two types of cascades based on presence or absence of early peaks in their sequence of inter-retweet intervals. We identify multiple diffusion localities associated with a cascade as it propagates over the network. Our studies reveal the transition of a cascade to a new locality facilitated by pivotal users that are highly cascade dependent following saturation of current locality. We propose an analytical model to show co-occurrence of first peaks with cascade migration to a new locality as well as predict locality saturation from interretweet intervals. Finally, we validate these claims from empirical data showing co-occurrence of first peaks and migration with good accuracy; we obtain even better accuracy for successfully classifying saturated and non-saturated diffusion localities from inter-retweet intervals.

Download

Temporal Sequence of Retweets Help to Detect Influential Nodes in Social Networks

IEEE Transactions on Computational Social Systems, 2019

Identification of influential users in online social networks allows to facilitate efficient info... more Identification of influential users in online social networks allows to facilitate efficient information diffusion to a large part of the network, thus benefiting diverse applications including viral marketing, disease control and news dissemination. Existing methods have mainly relied on the network structure only for the detection of influential users. In this paper, we enrich this approach by proposing a fast, efficient and unsupervised algorithm SmartInf to detect a set of influential users by identifying anchor nodes from temporal sequence of retweets in Twitter cascades. Such anchor nodes provide important signatures of tweet diffusion across multiple diffusion localities and hence act as precursors for detection of influential nodes 1 . The set of influential nodes identified by SmartInf have the capacity to expose the tweet to a large and diverse population, when targeted as seeds thereby maximizing the influence spread. Experimental evaluation on empirical datasets from Twitter show the superiority of SmartInf over state-of-the-art baselines in terms of infecting larger population; further, our evaluation shows that SmartInf is scalable to large-scale networks and is robust to missing data. Finally, we investigate the key factors behind the improved performance of SmartInf by testing our algorithm on a synthetic network using synthetic cascades simulated on this network. Our results reveal the effectiveness of SmartInf in identifying a diverse set of influential users that facilitate faster diffusion of tweets to a larger population.

Download

Listen to me, my neighbors or my friend? Role of complementary modalities for predicting business popularity in location based social networks

Computer Communications, 2019

Businesses are one of the major stakeholders of the location-based social network (LBSN) platform... more Businesses are one of the major stakeholders of the location-based social network (LBSN) platform. Predicting popularity of businesses in LBSN can help in future business planning and design of effective marketing strategies for business owners. In this paper, we introduce four simple modalities that serve as prime indicators of business popularity, namely, (a) social influence, (b) geographical proximity, (c) customer preference and (d) textual content of tips and reviews posted for a business and investigate their role on business popularity. Characterizing business popularity is ambiguous as there exist different viewpoints to measure popularity. We propose a principled methodology to properly label the popular and unpopular businesses by systematically defining popularity metrics specific to business categories. Social influence essentially represents the peer pressure for visiting certain businesses and eventually contributing to its popularity. Geographical proximity reveals that there are two types of customers visiting a business, namely, local & foreign customers and subsequently, we define the local dominated as well as foreign dominated businesses. On the other hand, customer preference reflects the inclination of a customer towards certain types (say 'Shopping', 'Hotels', 'Religious Organizations', 'Mass Media' etc) of businesses. Further, textual content reveals information about customers' experiences in visiting corresponding businesses. Interestingly, our investigation reveals that customers visit popular businesses amidst social pressure, however they visit unpopular businesses driven by their own personal preference. Moreover, we observe that local (foreign) customers play a major role in shaping the popularity of businesses in local (foreign, respectively) dominated cities. In addition, we observe that textual content of tips and reviews play a significant role in attracting customers to a business adding to its popularity. In a nutshell, this paper puts forward an important message that social influence, geographical proximity, customer preference and textual content exhibit strong complementary signals to predict business popularity. We evaluate the predictive power

Download

Effect of Information Propagation on Business Popularity: A Case Study on Yelp

2017 18th IEEE International Conference on Mobile Data Management (MDM), 2017

The penetration of smartphones and advancement of the location-based services have jointly contri... more The penetration of smartphones and advancement of the location-based services have jointly contributed to the popularity of location-based social networking platforms such as Foursquare and Yelp. Business owners are important stakeholders of such location-based social network (LBSN) platforms, for whom setting up new businesses at the right location has immense importance in making a business popular. Given a wide variety of businesses, a single metric may not correctly capture the business popularity, rather, popularity measure should be specific to geographical regions, business category etc. In this paper, we systematically define popularity metrics and use them to label diverse businesses available in Yelp dataset. Notably, information diffusion plays a major role in popularizing businesses, word of mouth communication across customers facilitates information spread. This paper concentrates on two key modalities that exhibit a strong signature of business popularity: social connections across customers, showing high correlation with corresponding business popularity, and geographical proximity, which reveals two types of customers, namely, local visitor and foreign visitor observed through a comprehensive study on Yelp dataset. Depending on the business type and category, either local or foreign visitors play important role in making a business popular. Finally, we leverage on these signatures to predict business popularity and develop a recommendation model suggesting top regions to business owners for starting popular businesses. We show that both the models outperform the state-of-the-art baseline algorithms.

LouvainNE

Proceedings of the 13th International Conference on Web Search and Data Mining, 2020

Network embedding, that aims to learn low-dimensional vector representation of nodes such that th... more Network embedding, that aims to learn low-dimensional vector representation of nodes such that the network structure is preserved, has gained significant research attention in recent years. However, most state-of-the-art network embedding methods are computationally expensive and hence unsuitable for representing nodes in billion-scale networks. In this paper, we present LouvainNE, a hierarchical clustering approach to network embedding. Precisely, we employ Louvain, an extremely fast and accurate community detection method, to build a hierarchy of successively smaller subgraphs. We obtain representations of individual nodes in the original graph at different levels of the hierarchy, then we aggregate these representations to learn the final embedding vectors. Our theoretical analysis shows that our proposed algorithm has quasi-linear runtime and memory complexity. Our extensive experimental evaluation, carried out on multiple real-world networks of different scales, demonstrates both (i) the scalability of our proposed approach that can handle graphs containing tens of billions of edges, as well as (ii) its effectiveness in performing downstream network mining tasks such as network reconstruction and node classification. • Computing methodologies → Machine learning algorithms; • Mathematics of computing → Graph algorithms.

Download

Uploads

Papers by Ayan Bhowmick

Log In