@inproceedings{xin2008www, title = {Tag-based Social Interest Discovery}, author = {Xin Li and Lei Guo and Yihong E. Zhao}, booktitle = {Proceedings of the 17th International World Wide Web Conference}, pages = {675-684}, publisher = {ACM}, year = 2008, url = {http://www2008.org/papers/pdf/p675-liA.pdf}, abstract = {The success and popularity of social network systems, such as del.icio.us, Facebook, MySpace, and YouTube, have generated many interesting and challenging problems to the research community. Among others, discovering social interests shared by groups of users is very important because it helps to connect people with common interests and encourages people to contribute and share more contents. The main challenge to solving this problem comes from the diffi- culty of detecting and representing the interest of the users. The existing approaches are all based on the online connections of users and so unable to identify the common interest of users who have no online connections. In this paper, we propose a novel social interest discovery approach based on user-generated tags. Our approach is motivated by the key observation that in a social network, human users tend to use descriptive tags to annotate the contents that they are interested in. Our analysis on a large amount of real-world traces reveals that in general, user-generated tags are consistent with the web content they are attached to, while more concise and closer to the understanding and judgments of human users about the content. Thus, patterns of frequent co-occurrences of user tags can be used to characterize and capture topics of user interests. We have developed an Internet Social Interest Discovery system, ISID, to discover the common user interests and cluster users and their saved URLs by different interest topics. Our evaluation shows that ISID can effectively cluster similar documents by interest topics and discover user communities with common interests no matter if they have any online connections.}, biburl = {http://www.bibsonomy.org/bibtex/242b4c94cff05ccef031235d661a7a77a/hotho}, keywords = {*** association clustering community del.icio.us detection folksonomy rules} } @article{McRae:2005:Behav-Res-Methods:16629288, title = {Semantic feature production norms for a large set of living and nonliving things}, author = {K McRae and G S Cree and M S Seidenberg and C McNorgan}, journal = {Behav Res Methods}, month = {Nov}, number = 4, pages = {547-559}, volume = 37, year = 2005, url = {http://www.ncbi.nlm.nih.gov/pubmed/16629288}, pmid = {16629288}, description = {Semantic feature production norms for a large set ...[Behav Res Methods. 2005] - PubMed Result}, abstract = {Semantic features have provided insight into numerous behavioral phenomena concerning concepts, categorization, and semantic memory in adults, children, and neuropsychological populations. Numerous theories and models in these areas are based on representations and computations involving semantic features. Consequently, empirically derived semantic feature production norms have played, and continue to play, a highly useful role in these domains. This article describes a set of feature norms collected from approximately 725 participants for 541 living (dog) and nonliving (chair) basic-level concepts, the largest such set of norms developed to date. This article describes the norms and numerous statistics associated with them. Our aim is to make these norms available to facilitate other research, while obviating the need to repeat the labor-intensive methods involved in collecting and analyzing such norms. The full set of norms may be downloaded from www.psychonomic.org/archive.}, biburl = {http://www.bibsonomy.org/bibtex/2936af12b025e37b0a6aac6bc103f58a3/hotho}, keywords = {dataset grounding ol ontology relation semantic toread} } @inproceedings{cone2006, title = {Cone Cluster Labeling for Support Vector Clustering}, author = {Sei-Hyung Lee and Karen M. Daniels}, booktitle = {Proceedings of 6th SIAM Conference on Data Mining}, month = {May}, pages = {484–488}, year = 2006, url = {http://www.siam.org/meetings/sdm06/proceedings/046lees.pdf}, added = {2007-04-29 16:58:13 +0200}, modified = {2007-06-19 18:52:22 +0200}, description = {BibSonomy::edit bibtex}, biburl = {http://www.bibsonomy.org/bibtex/276d1018ba398695e454d20de302de6e6/hotho}, keywords = {SVM clustering code toread} } @article{Smeulders00CBIR, title = {Content-Based Image Retrieval at the End of the Early Years}, address = {Washington, DC, USA}, author = {Arnold W. M. Smeulders and Marcel Worring and Simone Santini and Amarnath Gupta and Ramesh Jain}, journal = {IEEE Trans. Pattern Anal. Mach. Intell.}, month = {December}, number = 12, pages = {1349--1380}, publisher = {IEEE Computer Society}, volume = 22, year = 2000, url = {http://portal.acm.org/citation.cfm?id=357873}, id = {942093}, issn = {0162-8828}, priority = {2}, at = {2008-04-13 17:14:20}, doi = {10.1109/34.895972}, biburl = {http://www.bibsonomy.org/bibtex/2ff99ff85fdc2224d826dab75df21cf0d/hotho}, keywords = {image ir retrieval survey} } @article{datta2008, title = {Image Retrieval: Ideas, Influences, and Trends of the New Age}, author = {Ritendra Datta and Dhiraj Joshi and Jia Li and James Z. Wang}, journal = {ACM Computing Surveys}, number = 2, volume = 40, year = 2008, url = {http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/}, description = {Content Based Image Retrieval CBIR Survey Paper - 2008}, abstract = {We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. While the last decade laid foundation to such promise, it also paved the way for a large number of new techniques and systems, got many new people involved, and triggered stronger association of weakly related fields. In this paper, we survey almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation, and discuss the spawning of related sub-fields in the process. We also discuss significant challenges involved in the adaptation of existing image retrieval techniques to build systems that can be useful in the real-world. In retrospect of what has been achieved so far, we also conjecture what the future may hold for image retrieval research.}, biburl = {http://www.bibsonomy.org/bibtex/2278a48194bc9afbd298c36dd497a9821/hotho}, keywords = {images ir retrieval survey} } @article{Lerman:2007p3955, title = {Social Information Processing in Social News Aggregation}, author = {Kristina Lerman}, journal = {arXiv}, month = {Jan}, year = 2007, url = {http://arxiv.org/abs/cs.CY/0703087}, pmid = {11330701288966819101related:HY3tKMq8Pp0J}, added = {2008-02-07 01:06:26 +0100}, read = {Yes}, rating = {0}, uri = {papers://C3B117CD-23C4-4854-9426-AC96AFB113DA/Paper/p3955}, url = {file://localhost/Users/bertilhatt/Documents/Papers/Lerman/2007/Lerman%202007%20arXiv.pdf}, modified = {2008-02-07 02:25:10 +0100}, description = {March 2008}, abstract = {The rise of the social media sites, such as blogs, wikis, Digg and Flickr among others, underscores the transformation of the Web to a participatory medium in which users are collaboratively creating, evaluating and distributing information. The innovations introduced by social media has lead to a new paradigm for interacting with information, what we call 'social information processing'. In this paper, we study how social news aggregator Digg exploits social information processing to solve the problems of document recommendation and rating. First, we show, by tracking stories over time, that social networks play an important role in document recommendation. The second contribution of this paper consists of two mathematical models. The first model describes how collaborative rating and promotion of stories emerges from the independent decisions made by many users. The second model describes how a user's influence, the number of promoted stories and the user's social network, changes in time. We find qualitative agreement between predictions of the model and user data gathered from Digg.}, biburl = {http://www.bibsonomy.org/bibtex/27a080f640fa62fc81e73b9fab1e7447c/hotho}, keywords = {digg dynamics flickr network social toread} } @inproceedings{1281269, title = {A framework for community identification in dynamic social networks}, address = {New York, NY, USA}, author = {Chayant Tantipathananandh and Tanya Berger-Wolf and David Kempe}, booktitle = {KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining}, pages = {717--726}, publisher = {ACM}, year = 2007, url = {http://portal.acm.org/citation.cfm?doid=1281192.1281269}, location = {San Jose, California, USA}, isbn = {978-1-59593-609-7}, doi = {http://doi.acm.org/10.1145/1281192.1281269}, description = {A framework for community identification in dynamic social networks}, biburl = {http://www.bibsonomy.org/bibtex/227a4fb58300979d4dbe94e75422418bd/hotho}, keywords = {clustering community detection graph toread} } @article{keyhere, title = {A Cost-Sensitive Paradigm for Multiclass to Binary Decomposition Schemes}, author = {Claudio Marrocco and Francesco Tortorella}, journal = {Structural, Syntactic, and Statistical Pattern Recognition}, pages = {753--761}, year = 2004, url = {http://www.springerlink.com/content/5fdg88yxqvwale7j}, description = {SpringerLink - Book Chapter}, abstract = {An established technique to face a multiclass categorization problem is to reduce it into a set of two-class problems. To this aim, the main decomposition schemes employed are one vs. one, one vs. all and Error Correcting Output Coding. A point not yet considered in the research is how to apply these methods to a cost-sensitive classification that represents a significant aspect in many real problems. In this paper we propose a novel method which, starting from the cost matrix for the multi-class problem and from the code matrix employed, extracts a cost matrix for each of the binary subproblems induced by the coding matrix. In this way, it is possible to tune the single two-class classifier according to the cost matrix obtained and achieve an output from all the dichotomizers which takes into account the requirements of the original multi-class cost matrix. To evaluate the effectiveness of the method, a large number of tests has been performed on real data sets. The experiments results have shown a significant improvement in terms of classification cost, specially when using the ECOC scheme. ER -}, biburl = {http://www.bibsonomy.org/bibtex/2a234beda6a9a042041c89b21c8291eb0/hotho}, keywords = {class classifier multi svm} } @inproceedings{Chakrabarti:2004, title = {R-MAT: A Recursive Model for Graph Mining}, author = {D. Chakrabarti and Y. Zhan and C. Faloutsos}, booktitle = {SIAM International Conference on Data Mining}, year = 2004, url = {http://www.cs.cmu.edu/~christos/PUBLICATIONS/siam04.pdf}, biburl = {http://www.bibsonomy.org/bibtex/25e5cc221d7da719909f3bf8c507b0afc/hotho}, keywords = {graph mining model toread} } @inproceedings{anti2008krause, title = {The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems}, author = {Beate Krause and Andreas Hotho and Gerd Stumme}, booktitle = {Proc. of the Fourth International Workshop on Adversarial Information Retrieval on the Web}, year = 2008, url = {http://airweb.cse.lehigh.edu/2008/submissions/krause_2008_anti_social_tagger.pdf}, biburl = {http://www.bibsonomy.org/bibtex/203d349d70b578ca9ac3155f661151868/hotho}, keywords = {2008 bookmarking classification dm folksonomy mining ml myown social spam} }