@inproceedings{noauthororeditor, author = {Mirowski, Piotr and Ranzato, Marc'Aurelio and LeCun, Yann}, editor = {of the NIPS 2010 Workshop on Deep Learning, Proceedings}, interhash = {b7ce347e904a4ca3263cf6cc1e2253bd}, intrahash = {fc3e0e3af595f9a46df6bc9233df836f}, title = {Dynamic Auto-Encoders for Semantic Indexing}, url = {http://yann.lecun.com/exdb/publis/pdf/mirowski-nipsdl-10.pdf}, year = 2010 } @article{vorontsovtutorial, author = {Vorontsov, Konstantin and Potapenko, Anna}, interhash = {b3302a48be9b79342711884605ee3503}, intrahash = {12f451e98ef51ea1060565ab96e19e3c}, title = {Tutorial on Probabilistic Topic Modeling: Additive Regularization for Stochastic Matrix Factorization}, year = 2014 } @article{6542727, abstract = {In this paper, we propose a novel hierarchical generative model, named author-genre-topic model (AGTM), to perform satellite image annotation. Different from the existing author-topic model in which each author and topic are associated with the multinomial distributions over topics and words, in AGTM, each genre, author, and topic are associated with the multinomial distributions over authors, topics, and words, respectively. The bias of the distribution of the authors with respect to the topics can be rectified by incorporating the distribution of the genres with respect to the authors. Therefore, the classification accuracy of documents is improved when the information of genre is introduced. By representing the images with several visual words, the AGTM can be used for satellite image annotation. The labels of classes and scenes of the images correspond to the authors and the genres of the documents, respectively. The labels of classes and scenes of test images can be estimated, and the accuracy of satellite image annotation is improved when the information of scenes is introduced in the training images. Experimental results demonstrate the good performance of the proposed method.}, author = {Luo, Wang and Li, Hongliang and Liu, Guanghui and Zeng, Liaoyuan}, doi = {10.1109/TGRS.2013.2250978}, interhash = {4152c5c479a7eae90a4ee1f63dc89610}, intrahash = {a68906eb86024782ace5fe7a33d16522}, issn = {0196-2892}, journal = {Geoscience and Remote Sensing, IEEE Transactions on}, month = feb, number = 2, pages = {1356-1368}, title = {Semantic Annotation of Satellite Images Using Author - Genre - Topic Model}, url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=6542727&abstractAccess=no&userType=inst}, volume = 52, year = 2014 } @article{kataria2011context, abstract = {In a document network such as a citation network of scientific documents, web-logs etc., the content produced by authors exhibit their interest in certain topics. In addition some authors influence other authors' interests. In this work, we propose to model the influence of cited authors along with the interests of citing authors. Morover , we hypothesize that citations present in documents, the context surrounding the citation mention provides extra topical information about the cited authors. However, associating terms in the context to the cited authors remains an open problem. We propose novel document generation schemes that incorporate the context while simultaneously modeling the interests of citing authors and influence of the cited authors. Our experiments show significant improvements over baseline models for various evaluation criteria such as link prediction between document and cited author, and quantitatively explaining unseen text.}, author = {Kataria, Saurabh and Mitra, Prasenjit and Caragea, Cornelia and Giles, C.}, conference = {International Joint Conference on Artificial Intelligence}, interhash = {7496b4df1335fbc6aea691cecb65289d}, intrahash = {dc774d17ec721be6d32530d265f34539}, title = {Context Sensitive Topic Models for Author Influence in Document Networks}, url = {https://www.aaai.org/ocs/index.php/IJCAI/IJCAI11/paper/view/3140}, year = 2011 } @inproceedings{jardine2014topical, address = {Gothenburg, Sweden}, author = {Jardine, James and Teufel, Simone}, booktitle = {Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics}, interhash = {147a857a9dc2cc83a91b4f67908995a8}, intrahash = {f4620195b04beda98c3f7336c4b96dd5}, month = {April}, pages = {501--510}, publisher = {Association for Computational Linguistics}, title = {Topical PageRank: A Model of Scientific Expertise for Bibliographic Search}, url = {http://www.aclweb.org/anthology/E14-1053}, year = 2014 } @article{adomavicius2012impact, abstract = {This article investigates the impact of rating data characteristics on the performance of several popular recommendation algorithms, including user-based and item-based collaborative filtering, as well as matrix factorization. We focus on three groups of data characteristics: rating space, rating frequency distribution, and rating value distribution. A sampling procedure was employed to obtain different rating data subsamples with varying characteristics; recommendation algorithms were used to estimate the predictive accuracy for each sample; and linear regression-based models were used to uncover the relationships between data characteristics and recommendation accuracy. Experimental results on multiple rating datasets show the consistent and significant effects of several data characteristics on recommendation accuracy.}, acmid = {2151166}, address = {New York, NY, USA}, articleno = {3}, author = {Adomavicius, Gediminas and Zhang, Jingjing}, doi = {10.1145/2151163.2151166}, interhash = {53e424cc9502ebb33d38de1d04230196}, intrahash = {e41453a56391ca382f2298607b361208}, issn = {2158-656X}, issue_date = {April 2012}, journal = {ACM Trans. Manage. Inf. Syst.}, month = apr, number = 1, numpages = {17}, pages = {3:1--3:17}, publisher = {ACM}, title = {Impact of Data Characteristics on Recommender Systems Performance}, url = {http://doi.acm.org/10.1145/2151163.2151166}, volume = 3, year = 2012 } @inproceedings{conf/dis/PontiTK11, author = {Ponti, Giovanni and Tagarelli, Andrea and Karypis, George}, booktitle = {Discovery Science}, crossref = {conf/dis/2011}, editor = {Elomaa, Tapio and Hollmén, Jaakko and Mannila, Heikki}, ee = {http://dx.doi.org/10.1007/978-3-642-24477-3_21}, interhash = {1d2b8fd777a36c3c42c10dac886d5d25}, intrahash = {af476c498b77848fa7c8121c8955a307}, isbn = {978-3-642-24476-6}, pages = {247-261}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {A Statistical Model for Topically Segmented Documents.}, url = {http://dblp.uni-trier.de/db/conf/dis/dis2011.html#PontiTK11}, volume = 6926, year = 2011 } @article{journals/ml/DuBJ10, author = {Du, Lan and Buntine, Wray L. and Jin, Huidong}, ee = {http://dx.doi.org/10.1007/s10994-010-5197-4}, interhash = {f39304f04fa411cc2c9232aa7eb83b83}, intrahash = {286291dfe97008c5bda330ffc0b72af1}, journal = {Machine Learning}, number = 1, pages = {5-19}, title = {A segmented topic model based on the two-parameter Poisson-Dirichlet process.}, url = {http://dblp.uni-trier.de/db/journals/ml/ml81.html#DuBJ10}, volume = 81, year = 2010 } @inproceedings{Ramage:2009:LLS:1699510.1699543, abstract = {A significant portion of the world's text is tagged by readers on social bookmarking websites. Credit attribution is an inherent problem in these corpora because most pages have multiple tags, but the tags do not always apply with equal specificity across the whole document. Solving the credit attribution problem requires associating each word in a document with the most appropriate tags and vice versa. This paper introduces Labeled LDA, a topic model that constrains Latent Dirichlet Allocation by defining a one-to-one correspondence between LDA's latent topics and user tags. This allows Labeled LDA to directly learn word-tag correspondences. We demonstrate Labeled LDA's improved expressiveness over traditional LDA with visualizations of a corpus of tagged web pages from del.icio.us. Labeled LDA outperforms SVMs by more than 3 to 1 when extracting tag-specific document snippets. As a multi-label text classifier, our model is competitive with a discriminative baseline on a variety of datasets.}, acmid = {1699543}, address = {Stroudsburg, PA, USA}, author = {Ramage, Daniel and Hall, David and Nallapati, Ramesh and Manning, Christopher D.}, booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1 - Volume 1}, interhash = {45315f4da7b10debdca560506cf0d7ba}, intrahash = {6e7173f084e26bca9a8d2a1ab4a5b709}, isbn = {978-1-932432-59-6}, location = {Singapore}, numpages = {9}, pages = {248--256}, publisher = {Association for Computational Linguistics}, series = {EMNLP '09}, title = {Labeled LDA: A Supervised Topic Model for Credit Attribution in Multi-labeled Corpora}, url = {http://dl.acm.org/citation.cfm?id=1699510.1699543}, year = 2009 } @inproceedings{conf/kdd/HongYGD11, author = {Hong, Liangjie and Yin, Dawei and 0002, Jian Guo and 0001, Brian D. Davison}, booktitle = {KDD}, crossref = {conf/kdd/2011}, editor = {Apté, Chid and Ghosh, Joydeep and Smyth, Padhraic}, ee = {http://doi.acm.org/10.1145/2020408.2020485}, interhash = {35519287a72896f1adee0aaf14430dd8}, intrahash = {a636ba59e9c57611c070e30086b27592}, isbn = {978-1-4503-0813-7}, pages = {484-492}, publisher = {ACM}, title = {Tracking trends: incorporating term volume into temporal topic models.}, url = {http://dblp.uni-trier.de/db/conf/kdd/kdd2011.html#HongYGD11}, year = 2011 } @misc{kang2013lalda, abstract = {Social media users have finite attention which limits the number of incoming messages from friends they can process. Moreover, they pay more attention to opinions and recommendations of some friends more than others. In this paper, we propose LA-LDA, a latent topic model which incorporates limited, non-uniformly divided attention in the diffusion process by which opinions and information spread on the social network. We show that our proposed model is able to learn more accurate user models from users' social network and item adoption behavior than models which do not take limited attention into account. We analyze voting on news items on the social news aggregator Digg and show that our proposed model is better able to predict held out votes than alternative models. Our study demonstrates that psycho-socially motivated models have better ability to describe and predict observed behavior than models which only consider topics.}, author = {Kang, Jeon-Hyung and Lerman, Kristina and Getoor, Lise}, interhash = {18a900ae003a2aedb3879fcaaa4e89b6}, intrahash = {84ae222ddb615ca8ae9421a29c07a8f6}, note = {cite arxiv:1301.6277Comment: The 2013 International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction (SBP 2013)}, title = {LA-LDA: A Limited Attention Topic Model for Social Recommendation}, url = {http://arxiv.org/abs/1301.6277}, year = 2013 } @misc{lan2013joint, abstract = {Modern machine learning methods are critical to the development of large-scale personalized learning systems that cater directly to the needs of individual learners. The recently developed SPARse Factor Analysis (SPARFA) framework provides a new statistical model and algorithms for machine learning-based learning analytics, which estimate a learner's knowledge of the latent concepts underlying a domain, and content analytics, which estimate the relationships among a collection of questions and the latent concepts. SPARFA estimates these quantities given only the binary-valued graded responses to a collection of questions. In order to better interpret the estimated latent concepts, SPARFA relies on a post-processing step that utilizes user-defined tags (e.g., topics or keywords) available for each question. In this paper, we relax the need for user-defined tags by extending SPARFA to jointly process both graded learner responses and the text of each question and its associated answer(s) or other feedback. Our purely data-driven approach (i) enhances the interpretability of the estimated latent concepts without the need of explicitly generating a set of tags or performing a post-processing step, (ii) improves the prediction performance of SPARFA, and (iii) scales to large test/assessments where human annotation would prove burdensome. We demonstrate the efficacy of the proposed approach on two real educational datasets.}, author = {Lan, Andrew S. and Studer, Christoph and Waters, Andrew E. and Baraniuk, Richard G.}, interhash = {911707523671c994e5c3fe63c3df5c4a}, intrahash = {2a8df43258181ed85e5d43b489fd45fb}, note = {cite arxiv:1305.1956}, title = {Joint Topic Modeling and Factor Analysis of Textual Information and Graded Response Data}, url = {http://arxiv.org/abs/1305.1956}, year = 2013 } @article{piatkowski2013spatiotemporal, author = {Piatkowski, Nico and Lee, Sangkyun and Morik, Katharina}, doi = {10.1007/s10994-013-5399-7}, interhash = {314e29a1c444118b8a4e8d2ba7ab6336}, intrahash = {eed8d4fcd9cfc30c01c1bf72e8e9cdbb}, issn = {0885-6125}, journal = {Machine Learning}, language = {English}, number = 1, pages = {115-139}, publisher = {Springer US}, title = {Spatio-temporal random fields: compressible representation and distributed estimation}, url = {http://dx.doi.org/10.1007/s10994-013-5399-7}, volume = 93, year = 2013 } @inproceedings{ls_leimeister, address = {Helsinki, Finland (accepted for publication)}, author = {Bitzer, Philipp and Weiß, Frank and Leimeister, Jan Marco}, booktitle = {Eighth International Conference on Design Science Research in Information Systems and Technology (DESRIST)}, interhash = {48a19913ff4a7fda6f2ffac9c1b0af08}, intrahash = {ecc572acde1b82bc3db34fcfd34c4e31}, title = {Towards a Reference Model for a Productivity-optimized Delivery of Technology Mediated }, year = 2013 } @misc{titov2008modeling, abstract = {In this paper we present a novel framework for extracting the ratable aspects of objects from online user reviews. Extracting such aspects is an important challenge in automatically mining product opinions from the web and in generating opinion-based summaries of user reviews. Our models are based on extensions to standard topic modeling methods such as LDA and PLSA to induce multi-grain topics. We argue that multi-grain models are more appropriate for our task since standard models tend to produce topics that correspond to global properties of objects (e.g., the brand of a product type) rather than the aspects of an object that tend to be rated by a user. The models we present not only extract ratable aspects, but also cluster them into coherent topics, e.g., `waitress' and `bartender' are part of the same topic `staff' for restaurants. This differentiates it from much of the previous work which extracts aspects through term frequency analysis with minimal clustering. We evaluate the multi-grain models both qualitatively and quantitatively to show that they improve significantly upon standard topic models.}, author = {Titov, Ivan and McDonald, Ryan}, interhash = {00cbf1df09c3f2c65d5a31a0537aed3f}, intrahash = {f3286f5efa0115f465563d0259c32255}, note = {cite arxiv:0801.1063}, title = {Modeling Online Reviews with Multi-grain Topic Models}, url = {http://arxiv.org/abs/0801.1063}, year = 2008 } @article{Juhos20081488, abstract = {The main aim of this paper is to predict NO and NO2 concentrations four days in advance comparing two artificial intelligence learning methods, namely, Multi-Layer Perceptron and Support Vector Machines on two kinds of spatial embedding of the temporal time series. Hourly values of NO and NO2 concentrations, as well as meteorological variables were recorded in a cross-road monitoring station with heavy traffic in Szeged in order to build a model for predicting NO and NO2 concentrations several hours in advance. The prediction of NO and NO2 concentrations was performed partly on the basis of their past values, and partly on the basis of temperature, humidity and wind speed data. Since NO can be predicted more accurately, its values were considered primarily when forecasting NO2. Time series prediction can be interpreted in a way that is suitable for artificial intelligence learning. Two effective learning methods, namely, Multi-Layer Perceptron and Support Vector Regression are used to provide efficient non-linear models for NO and NO2 times series predictions. Multi-Layer Perceptron is widely used to predict these time series, but Support Vector Regression has not yet been applied for predicting NO and NO2 concentrations. Grid search is applied to select the best parameters for the learners. To get rid of the curse of dimensionality of the spatial embedding of the time series Principal Component Analysis is taken to reduce the dimension of the embedded data. Three commonly used linear algorithms were considered as references: one-day persistence, average of several-day persistence and linear regression. Based on the good results of the average of several-day persistence, a prediction scheme was introduced, which forms weighted averages instead of simple ones. The optimization of these weights was performed with linear regression in linear case and with the learning methods mentioned in non-linear case. Concerning the NO predictions, the non-linear learning methods give significantly better predictions than the reference linear methods. In the case of NO2 the improvement of the prediction is considerable; however, it is less notable than for NO.}, author = {Juhos, István and Makra, László and Tóth, Balázs}, doi = {10.1016/j.simpat.2008.08.006}, interhash = {b8e240cb2c8bb4d0f42aeda944a3ed15}, intrahash = {70d6cf3c171445620c5024658516ac44}, issn = {1569-190X}, journal = {Simulation Modelling Practice and Theory}, number = 9, pages = {1488 - 1502}, title = {Forecasting of traffic origin NO and NO2 concentrations by Support Vector Machines and neural networks using Principal Component Analysis}, url = {http://www.sciencedirect.com/science/article/pii/S1569190X08001585}, volume = 16, year = 2008 } @article{Zhang20125759, abstract = {Social tagging is one of the most important ways to organize and index online resources. Recommendation in social tagging systems, e.g. tag recommendation, item recommendation and user recommendation, is used to improve the quality of tags and to ease the tagging or searching process. Existing works usually provide recommendations by analyzing relation information in social tagging systems, suffering a lot from the over sparse problem. These approaches ignore information contained in the content of resources, which we believe should be considered to improve recommendation quality and to deal with the over sparse problem. In this paper we propose a recommendation approach for social tagging systems that combines content and relation analysis in a single model. By modeling the generating process of social tagging systems in a latent Dirichlet allocation approach, we build a fully generative model for social tagging, leverage it to estimate the relation between users, tags and resources and achieve tag, item and user recommendation tasks. The model is evaluated using a CiteULike data snapshot, and results show improvements in metrics for various recommendation tasks.}, author = {Zhang, Yin and Zhang, Bin and Gao, Kening and Guo, Pengwei and Sun, Daming}, doi = {10.1016/j.physa.2012.05.013}, interhash = {088ad59c786579d399aaee48db5e6a7a}, intrahash = {84f824839090a5e20394b85a9e1cef08}, issn = {0378-4371}, journal = {Physica A: Statistical Mechanics and its Applications}, number = 22, pages = {5759 - 5768}, title = {Combining content and relation analysis for recommendation in social tagging systems}, url = {http://www.sciencedirect.com/science/article/pii/S0378437112003846}, volume = 391, year = 2012 } @inproceedings{Rudolph:2010:CMM:1858681.1858774, abstract = {We propose CMSMs, a novel type of generic compositional models for syntactic and semantic aspects of natural language, based on matrix multiplication. We argue for the structural and cognitive plausibility of this model and show that it is able to cover and combine various common compositional NLP approaches ranging from statistical word space models to symbolic grammar formalisms.}, acmid = {1858774}, address = {Stroudsburg, PA, USA}, author = {Rudolph, Sebastian and Giesbrecht, Eugenie}, booktitle = {Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics}, interhash = {6594500d38a361829aeb3ef7889a1709}, intrahash = {05ec57c39e9b945deb674c3b616eac8f}, location = {Uppsala, Sweden}, numpages = {10}, pages = {907--916}, publisher = {Association for Computational Linguistics}, series = {ACL '10}, title = {Compositional matrix-space models of language}, url = {http://dl.acm.org/citation.cfm?id=1858681.1858774}, year = 2010 } @inproceedings{chan2009mathematical, abstract = {Human computation is a technique that makes use of human abilities for computation to solve problems. Social games use the power of the Internet game players to solve human computation problems. In previous works, many social games were proposed and were quite successful, but no formal framework exists for designing social games in general. A formal framework is important because it lists out the design elements of a social game, the characteristics of a human computation problem, and their relationships. With a formal framework, it simplifies the way to design a social game for a specific problem. In this paper, our contributions are: (1) formulate a formal model on social games, (2) analyze the framework and derive some interesting properties based on model's interactions, (3) illustrate how some current social games can be realized with the proposed formal model, and (4) describe how to design a social game for solving a specific problem with the use of the proposed formal model. This paper presents a set of design guidelines derived from the formal model and demonstrates that the model can help to design a social game for solving a specific problem in a formal and structural way.}, author = {Chan, Kam Tong and King, I. and Yuen, Man-Ching}, booktitle = {Proceedings of the International Conference on Computational Science and Engineering, CSE '09}, doi = {10.1109/CSE.2009.166}, interhash = {a54732b662bcb0d763139a38f6525b56}, intrahash = {216d582316e970eb498423ee8448edbe}, month = aug, pages = {1205--1210}, title = {Mathematical Modeling of Social Games}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5283086&tag=1}, volume = 4, year = 2009 } @article{ls_leimeister, author = {Klendauer, Ruth and Berkovich, Marina and Gelvin, Richard and Leimeister, Jan Marco and Krcmar, Helmut}, interhash = {deaa7650bc663349e5af3df4f25c1cee}, intrahash = {4f1f2764d33073b1d87c30a06ccf6ba9}, journal = {Information Systems Journal}, note = {EXT13}, number = 6, pages = {475-503}, title = {Towards a competency model for requirements analysts }, url = {http://pubs.wi-kassel.de/wp-content/uploads/2013/03/JML_348.pdf}, volume = 22, year = 2012 }