@inproceedings{conf/ai/ShafieiM08, author = {Shafiei, M. Mahdi and Milios, Evangelos E.}, booktitle = {Canadian Conference on AI}, crossref = {conf/ai/2008}, editor = {Bergler, Sabine}, ee = {http://dx.doi.org/10.1007/978-3-540-68825-9_27}, interhash = {1ed1fddf0ac4762ea8debac2ee80b936}, intrahash = {80e27cd4ea288b0ab6bcc1c67841364e}, isbn = {978-3-540-68821-1}, pages = {283-295}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {A Statistical Model for Topic Segmentation and Clustering.}, url = {http://dblp.uni-trier.de/db/conf/ai/ai2008.html#ShafieiM08}, volume = 5032, year = 2008 } @inproceedings{conf/pkdd/BalasubramanyanDC13, author = {Balasubramanyan, Ramnath and Dalvi, Bhavana Bharat and Cohen, William W.}, booktitle = {ECML/PKDD (2)}, crossref = {conf/pkdd/2013-2}, editor = {Blockeel, Hendrik and Kersting, Kristian and Nijssen, Siegfried and Zelezný, Filip}, ee = {http://dx.doi.org/10.1007/978-3-642-40991-2_40}, interhash = {9a32b7cc059a500ea302d0aa65036682}, intrahash = {e56623d21a1b7bcb442cd15fe098bb70}, isbn = {978-3-642-40990-5}, pages = {628-642}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {From Topic Models to Semi-supervised Learning: Biasing Mixed-Membership Models to Exploit Topic-Indicative Features in Entity Clustering.}, url = {http://dblp.uni-trier.de/db/conf/pkdd/pkdd2013-2.html#BalasubramanyanDC13}, volume = 8189, year = 2013 } @incollection{bleigjt03, address = {Cambridge, MA}, author = {Blei, D. M. and Griffiths, T. L. and Jordan, M. I. and Tenenbaum, J. B.}, booktitle = {Advances in {N}eural {I}nformation {P}rocessing {S}ystems 16}, interhash = {f185b4657e25c733ee613bece516b3c5}, intrahash = {3e438204424fa2c6e8915bd8f0baf112}, publisher = {MIT Press}, title = {Hierarchical topic models and the nested {C}hinese restaurant process}, year = 2004 } @misc{goldenberg2009survey, abstract = {Networks are ubiquitous in science and have become a focal point for discussion in everyday life. Formal statistical models for the analysis of network data have emerged as a major topic of interest in diverse areas of study, and most of these involve a form of graphical representation. Probability models on graphs date back to 1959. Along with empirical studies in social psychology and sociology from the 1960s, these early works generated an active network community and a substantial literature in the 1970s. This effort moved into the statistical literature in the late 1970s and 1980s, and the past decade has seen a burgeoning network literature in statistical physics and computer science. The growth of the World Wide Web and the emergence of online networking communities such as Facebook, MySpace, and LinkedIn, and a host of more specialized professional network communities has intensified interest in the study of networks and network data. Our goal in this review is to provide the reader with an entry point to this burgeoning literature. We begin with an overview of the historical development of statistical network modeling and then we introduce a number of examples that have been studied in the network literature. Our subsequent discussion focuses on a number of prominent static and dynamic network models and their interconnections. We emphasize formal model descriptions, and pay special attention to the interpretation of parameters and their estimation. We end with a description of some open problems and challenges for machine learning and statistics.}, author = {Goldenberg, Anna and Zheng, Alice X and Fienberg, Stephen E and Airoldi, Edoardo M}, interhash = {bab22de06306d84cf357aadf48982d87}, intrahash = {5e341981218d7cd89416c3371d56c794}, note = {cite arxiv:0912.5410Comment: 96 pages, 14 figures, 333 references}, title = {A survey of statistical network models}, url = {http://arxiv.org/abs/0912.5410}, year = 2009 } @inproceedings{journals/jmlr/ChangB09, author = {Chang, Jonathan and Blei, David M.}, booktitle = {AISTATS}, crossref = {conf/aistats/2009}, editor = {Dyk, David A. Van and Welling, Max}, ee = {http://www.jmlr.org/proceedings/papers/v5/chang09a.html}, interhash = {f3431fd69b315a22422a2c0f15ee0b71}, intrahash = {86f665b74ecabb56e81542e0f052a331}, pages = {81-88}, publisher = {JMLR.org}, series = {JMLR Proceedings}, title = {Relational Topic Models for Document Networks.}, url = {http://dblp.uni-trier.de/db/journals/jmlr/jmlrp5.html#ChangB09}, volume = 5, year = 2009 } @inproceedings{Zheleva:2010:SMM:1772690.1772794, abstract = {User experience in social media involves rich interactions with the media content and other participants in the community. In order to support such communities, it is important to understand the factors that drive the users' engagement. In this paper we show how to define statistical models of different complexity to describe patterns of song listening in an online music community. First, we adapt the LDA model to capture music taste from listening activities across users and identify both the groups of songs associated with the specific taste and the groups of listeners who share the same taste. Second, we define a graphical model that takes into account listening sessions and captures the listening moods of users in the community. Our session model leads to groups of songs and groups of listeners with similar behavior across listening sessions and enables faster inference when compared to the LDA model. Our experiments with the data from an online media site demonstrate that the session model is better in terms of the perplexity compared to two other models: the LDA-based taste model that does not incorporate cross-session information and a baseline model that does not use latent groupings of songs.}, acmid = {1772794}, address = {New York, NY, USA}, author = {Zheleva, Elena and Guiver, John and Mendes Rodrigues, Eduarda and Mili\'{c}-Frayling, Nata\v{s}a}, booktitle = {Proceedings of the 19th international conference on World wide web}, doi = {10.1145/1772690.1772794}, interhash = {7386777403403d0c1b524d1a7cf8065c}, intrahash = {3a244bf0cd60252269e3c36530e34e8f}, isbn = {978-1-60558-799-8}, location = {Raleigh, North Carolina, USA}, numpages = {10}, pages = {1019--1028}, publisher = {ACM}, series = {WWW '10}, title = {Statistical models of music-listening sessions in social media}, url = {http://doi.acm.org/10.1145/1772690.1772794}, year = 2010 } @inproceedings{ls_leimeister, address = {Cologne, Germany}, author = {Gierczak, Michael and Söllner, Matthias and Leimeister, Jan Marco}, booktitle = {ConLife 2012 Academic Conference}, interhash = {55d8152a9bc0f44d511c03baadb60426}, intrahash = {36de6094774092f9602aa515dc783599}, note = 339, title = {Untersuchung bestehender Geschäftsmodelle etablierter Cloud Anbieter}, url = {http://pubs.wi-kassel.de/wp-content/uploads/2013/03/JML_360.pdf}, year = 2012 } @article{fu2008models, abstract = {The single most important bibliometric criterion for judging the impact of biomedical papers and their authors work is the number of citations received which is commonly referred to as citation count. This metric however is unavailable until several years after publication time. In the present work, we build computer models that accurately predict citation counts of biomedical publications within a deep horizon of ten years using only predictive information available at publication time. Our experiments show that it is indeed feasible to accurately predict future citation counts with a mixture of content-based and bibliometric features using machine learning methods. The models pave the way for practical prediction of the long-term impact of publication, and their statistical analysis provides greater insight into citation behavior.}, author = {Fu, Lawrence D. and Aliferis, Constantin}, interhash = {1eb972fa9ba9e255d6889b01532ea767}, intrahash = {39d155a532108bc71437451e31287943}, journal = {AMIA Annu Symp Proc}, pages = {222-226}, pmid = {18999029}, title = {Models for predicting and explaining citation count of biomedical articles}, url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2656101/}, year = 2008 } @inproceedings{conf/icdm/AlSumaitBD08, author = {AlSumait, Loulwah and Barbará, Daniel and Domeniconi, Carlotta}, booktitle = {ICDM}, crossref = {conf/icdm/2008}, date = {2009-02-20}, ee = {http://dx.doi.org/10.1109/ICDM.2008.140}, interhash = {e46dde3d53c823afeeb7604f1991b661}, intrahash = {980e5cf0b3db547cf47c2c203734ac83}, pages = {3-12}, publisher = {IEEE Computer Society}, title = {On-line LDA: Adaptive Topic Models for Mining Text Streams with Applications to Topic Detection and Tracking.}, url = {http://dblp.uni-trier.de/db/conf/icdm/icdm2008.html#AlSumaitBD08}, year = 2008 } @article{pilz-named, author = {Pilz, A. and Paa{\ss}, G. and Augustin, G. St}, interhash = {056d7a3a9a77c31044e996acfb23cc8c}, intrahash = {f956b02691b503629c6742b3e61489da}, title = {{Named Entity Resolution Using Automatically Extracted Semantic Information}}, url = {http://scholar.google.de/scholar.bib?q=info:3tHCLbaX3_sJ:scholar.google.com/&output=citation&hl=de&ct=citation&cd=0}, year = 2009 } @article{journals/jmlr/BanerjeeMDG05, author = {Banerjee, Arindam and Merugu, Srujana and Dhillon, Inderjit S. and Ghosh, Joydeep}, date = {2007-02-21}, ee = {http://www.jmlr.org/papers/v6/banerjee05b.html}, interhash = {50d46127d134382ca84699ce24171c3f}, intrahash = {bba5d5241acf3ec9eea3f869a832c629}, journal = {Journal of Machine Learning Research}, pages = {1705-1749}, title = {Clustering with Bregman Divergences.}, url = {http://dblp.uni-trier.de/db/journals/jmlr/jmlr6.html#BanerjeeMDG05}, volume = 6, year = 2005 } @article{Dempster77maximumlikelihood, abstract = {A broadly applicable algorithm for computing maximum likelihood estimates from incomplete data is presented at various levels of generality. Theory showing the monotone behaviour of the likelihood and convergence of the algorithm is derived. Many examples are sketched, including missing value situations, applications to grouped, censored or truncated data, finite mixture models, variance component estimation, hyperparameter estimation, iteratively reweighted least squares and factor analysis. }, author = {Dempster, A. P. and Laird, N. M. and Rubin, D. B.}, interhash = {6a3c3e7e36b05f7855a57eab65f93593}, intrahash = {c0eee49f4f3379bac851721935e5141a}, journal = {JOURNAL OF THE ROYAL STATISTICAL SOCIETY, SERIES B}, number = 1, pages = {1--38}, title = {Maximum likelihood from incomplete data via the EM algorithm}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.133.4884}, volume = 39, year = 1977 } @article{nallapati2008link, author = {Nallapati, R. and Cohen, W.}, booktitle = {International Conference for Weblogs and Social Media}, interhash = {fc5e49ebae9358381b43981b6794158b}, intrahash = {a1f50ddb9b2734e224d4c4ea0140c7cd}, title = {{Link-PLSA-LDA: A new unsupervised model for topics and influence of blogs}}, url = {http://scholar.google.de/scholar.bib?q=info:WFXUMUlnnKwJ:scholar.google.com/&output=citation&hl=de&ct=citation&cd=0}, year = 2008 } @article{bishop1998latent, author = {Bishop, C.M.}, interhash = {3d556e46becabe2ec132942af1409079}, intrahash = {8c95ee19fc4410c654b624cb9bd6ff57}, journal = {Learning in graphical models}, title = {{Latent variable models}}, url = {http://scholar.google.de/scholar.bib?q=info:fwgN--1AHXsJ:scholar.google.com/&output=citation&hl=de&ct=citation&cd=0}, year = 1998 } @article{339252, address = {Hingham, MA, USA}, author = {Jordan, Michael I. and Ghahramani, Zoubin and Jaakkola, Tommi S. and Saul, Lawrence K.}, doi = {http://dx.doi.org/10.1023/A:1007665907178}, interhash = {f305ddebfd438a2575f09d72467a81c9}, intrahash = {30a0c13528ae353d38e6c8aed9db7821}, issn = {0885-6125}, journal = {Mach. Learn.}, number = 2, pages = {183--233}, publisher = {Kluwer Academic Publishers}, title = {An Introduction to Variational Methods for Graphical Models}, url = {http://portal.acm.org/citation.cfm?id=339248.339252}, volume = 37, year = 1999 } @inbook{steyvers_griffiths07, author = {Steyvers, M. and Griffiths, T.}, chapter = {Probabilistic topic models}, editor = {Landauer, T. and McNamara, S. Dennis and Kintsch, W.}, interhash = {4b2ab9b5eecc61ba49087d932b25f11c}, intrahash = {ab33268b60e8774bdfe46cd50a970fa3}, owner = {gregor}, publisher = {Laurence Erlbaum}, timestamp = {2008.02.26}, title = {Latent Semantic Analysis: A Road to Meaning}, year = 2007 } @article{mccallum2007topic, author = {McCallum, A. and Wang, X. and Corrada-Emmanuel, A.}, interhash = {56511b795458d88811bffd6ad8ec1e89}, intrahash = {e7a6d3c9bd46ddc77a62e04d35aff330}, journal = {Journal of Artificial Intelligence Research}, pages = {249--272}, title = {{Topic and role discovery in social networks with experiments on enron and academic email}}, url = {http://scholar.google.de/scholar.bib?q=info:GVi_TXpyWz8J:scholar.google.com/&output=citation&hl=de&ct=citation&cd=0}, volume = 30, year = 2007 } @inproceedings{shafiei_milios06, address = {Washington, DC, USA}, author = {Shafiei, M. Mahdi and Milios, Evangelos E.}, bdsk-url-1 = {http://dx.doi.org/10.1109/ICDM.2006.94}, booktitle = {ICDM '06: Proceedings of the Sixth International Conference on Data Mining}, doi = {http://dx.doi.org/10.1109/ICDM.2006.94}, interhash = {5850c178c4393ec9c7ea8b0f7f9271c5}, intrahash = {f36c376d49e03acd1cae83c758327943}, isbn = {0-7695-2701-9}, owner = {gregor}, pages = {542--551}, publisher = {IEEE Computer Society}, timestamp = {2008.04.25}, title = {Latent {D}irichlet Co-Clustering}, year = 2006 } @article{gregor2009generic, abstract = {This article contributes a generic model of topic models. To define the problem space, general characteristics for this class of models are derived, which give rise to a representation of topic models as “mixture networks”, a domain-specific compactalternative to Bayesian networks. Besides illustrating the interconnection of mixtures in topic models, the benefit of thisrepresentation is its straight-forward mapping to inference equations and algorithms, which is shown with the derivation andimplementation of a generic Gibbs sampling algorithm.}, author = {Heinrich, Gregor}, interhash = {9509ac0016837f04415cfcb5ef2ea93c}, intrahash = {dd184722f6239798835404daa73f9d36}, journal = {Machine Learning and Knowledge Discovery in Databases}, pages = {517--532}, title = {A Generic Approach to Topic Models}, url = {http://dx.doi.org/10.1007/978-3-642-04180-8_51}, year = 2009 } @incollection{griffiths_05, address = {Cambridge, MA}, author = {{Griffiths}, Thomas L. and {Steyvers}, Mark and {Blei}, David M. and {Tenenbaum}, Joshua B.}, booktitle = {Advances in Neural Information Processing Systems 17}, editor = {Saul, Lawrence K. and Weiss, Yair and Bottou, {L\'{e}on}}, interhash = {7d2594aa4b9905370ef001eebb6461b7}, intrahash = {dd89145403b46fc5315d3206f89bb09b}, owner = {heinrich}, pages = {537-544}, publisher = {MIT Press}, title = {Integrating Topics and Syntax}, volume = 17, year = 2005 }