The Experts below are selected from a list of 41550 Experts worldwide ranked by ideXlab platform

Hsing Kenneth Cheng - One of the best experts on this subject based on the ideXlab platform.

  • Estimating Social Influences from Social Networking Sites—Articulated Friendships versus Communication Interactions
    Decision Sciences, 2015
    Co-Authors: Praveen Pathak, Hsing Kenneth Cheng
    Abstract:

    Despite the ubiquity of social networking sites, the online social networking industry is in search of effective marketing strategies to better profit from their established user base. Social media marketing strategies build on the premise that the social network of online users can be predicted and social influences among online users can be estimated. However, the existence of various heterogeneous social interactions on social networking sites presents a challenge for social network prediction and social influence estimation. In this article we draw upon the literatures on self-presentation on social networking sites and signaling in online social networking to categorize six heterogeneous online social interactions on social networking sites into two types—articulated friendships and communication interactions. This article provides empirical evidence for the differences between articulated friendships and communication interactions and the corresponding articulated and communication networks. In order to compare the impacts of the social influences based on these two networks, we utilize support vector machines to build a classifier to predict virtual Community Membership and we further estimate the marginal effects of these social influences using a two-stage probit least squares method. We find significant explanatory power of social influences in predicting virtual Community Membership. Although the communication network is much sparser than the articulated network, social influences based on the communication network achieve similar performance as the articulated network. These findings provide important implications for social media marketing as well as the management of virtual communities.

Mari Ostendorf - One of the best experts on this subject based on the ideXlab platform.

  • Community member retrieval on social media using textual information
    North American Chapter of the Association for Computational Linguistics, 2018
    Co-Authors: Aaron Jaech, Shobhit Hathi, Mari Ostendorf
    Abstract:

    This paper addresses the problem of Community Membership detection using only text features in a scenario where a small number of positive labeled examples defines the Community. The solution introduces an unsupervised proxy task for learning user embeddings: user re-identification. Experiments with 16 different communities show that the resulting embeddings are more effective for Community Membership identification than common unsupervised representations.

  • NAACL-HLT (2) - Community Member Retrieval on Social Media Using Textual Information
    Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume , 2018
    Co-Authors: Aaron Jaech, Shobhit Hathi, Mari Ostendorf
    Abstract:

    This paper addresses the problem of Community Membership detection using only text features in a scenario where a small number of positive labeled examples defines the Community. The solution introduces an unsupervised proxy task for learning user embeddings: user re-identification. Experiments with 16 different communities show that the resulting embeddings are more effective for Community Membership identification than common unsupervised representations.

Jon Kleinberg - One of the best experts on this subject based on the ideXlab platform.

  • Community Membership identification from small seed sets
    Knowledge Discovery and Data Mining, 2014
    Co-Authors: Isabel M Kloumann, Jon Kleinberg
    Abstract:

    In many applications we have a social network of people and would like to identify the members of an interesting but unlabeled group or Community. We start with a small number of exemplar group members -- they may be followers of a political ideology or fans of a music genre -- and need to use those examples to discover the additional members. This problem gives rise to the seed expansion problem in Community detection: given example Community members, how can the social graph be used to predict the identities of remaining, hidden Community members? In contrast with global Community detection (graph partitioning or covering), seed expansion is best suited for identifying communities locally concentrated around nodes of interest. A growing body of work has used seed expansion as a scalable means of detecting overlapping communities. Yet despite growing interest in seed expansion, there are divergent approaches in the literature and there still isn't a systematic understanding of which approaches work best in different domains. Here we evaluate several variants and uncover subtle trade-offs between different approaches. We explore which properties of the seed set can improve performance, focusing on heuristics that one can control in practice. As a consequence of this systematic understanding we have found several opportunities for performance gains. We also consider an adaptive version in which requests are made for additional Membership labels of particular nodes, such as one finds in field studies of social communities. This leads to interesting connections and contrasts with active learning and the trade-offs of exploration and exploitation. Finally, we explore topological properties of communities and seed sets that correlate with algorithm performance, and explain these empirical observations with theoretical ones. We evaluate our methods across multiple domains, using publicly available datasets with labeled, ground-truth communities.

  • KDD - Community Membership identification from small seed sets
    Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 2014
    Co-Authors: Isabel M Kloumann, Jon Kleinberg
    Abstract:

    In many applications we have a social network of people and would like to identify the members of an interesting but unlabeled group or Community. We start with a small number of exemplar group members -- they may be followers of a political ideology or fans of a music genre -- and need to use those examples to discover the additional members. This problem gives rise to the seed expansion problem in Community detection: given example Community members, how can the social graph be used to predict the identities of remaining, hidden Community members? In contrast with global Community detection (graph partitioning or covering), seed expansion is best suited for identifying communities locally concentrated around nodes of interest. A growing body of work has used seed expansion as a scalable means of detecting overlapping communities. Yet despite growing interest in seed expansion, there are divergent approaches in the literature and there still isn't a systematic understanding of which approaches work best in different domains. Here we evaluate several variants and uncover subtle trade-offs between different approaches. We explore which properties of the seed set can improve performance, focusing on heuristics that one can control in practice. As a consequence of this systematic understanding we have found several opportunities for performance gains. We also consider an adaptive version in which requests are made for additional Membership labels of particular nodes, such as one finds in field studies of social communities. This leads to interesting connections and contrasts with active learning and the trade-offs of exploration and exploitation. Finally, we explore topological properties of communities and seed sets that correlate with algorithm performance, and explain these empirical observations with theoretical ones. We evaluate our methods across multiple domains, using publicly available datasets with labeled, ground-truth communities.

Praveen Pathak - One of the best experts on this subject based on the ideXlab platform.

  • Estimating Social Influences from Social Networking Sites—Articulated Friendships versus Communication Interactions
    Decision Sciences, 2015
    Co-Authors: Praveen Pathak, Hsing Kenneth Cheng
    Abstract:

    Despite the ubiquity of social networking sites, the online social networking industry is in search of effective marketing strategies to better profit from their established user base. Social media marketing strategies build on the premise that the social network of online users can be predicted and social influences among online users can be estimated. However, the existence of various heterogeneous social interactions on social networking sites presents a challenge for social network prediction and social influence estimation. In this article we draw upon the literatures on self-presentation on social networking sites and signaling in online social networking to categorize six heterogeneous online social interactions on social networking sites into two types—articulated friendships and communication interactions. This article provides empirical evidence for the differences between articulated friendships and communication interactions and the corresponding articulated and communication networks. In order to compare the impacts of the social influences based on these two networks, we utilize support vector machines to build a classifier to predict virtual Community Membership and we further estimate the marginal effects of these social influences using a two-stage probit least squares method. We find significant explanatory power of social influences in predicting virtual Community Membership. Although the communication network is much sparser than the articulated network, social influences based on the communication network achieve similar performance as the articulated network. These findings provide important implications for social media marketing as well as the management of virtual communities.

Aaron Jaech - One of the best experts on this subject based on the ideXlab platform.

  • Community member retrieval on social media using textual information
    North American Chapter of the Association for Computational Linguistics, 2018
    Co-Authors: Aaron Jaech, Shobhit Hathi, Mari Ostendorf
    Abstract:

    This paper addresses the problem of Community Membership detection using only text features in a scenario where a small number of positive labeled examples defines the Community. The solution introduces an unsupervised proxy task for learning user embeddings: user re-identification. Experiments with 16 different communities show that the resulting embeddings are more effective for Community Membership identification than common unsupervised representations.

  • NAACL-HLT (2) - Community Member Retrieval on Social Media Using Textual Information
    Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume , 2018
    Co-Authors: Aaron Jaech, Shobhit Hathi, Mari Ostendorf
    Abstract:

    This paper addresses the problem of Community Membership detection using only text features in a scenario where a small number of positive labeled examples defines the Community. The solution introduces an unsupervised proxy task for learning user embeddings: user re-identification. Experiments with 16 different communities show that the resulting embeddings are more effective for Community Membership identification than common unsupervised representations.