Topic model methods for automatically identifying out-of-scope resources Export

@inproceedings{citeulike:5089969, abstract = {Recent years have seen the rise of subject-themed digital libraries, such as the NSDL pathways and the Digital Library for Earth System Education (DLESE). These libraries often need to manually verify that contributed resources cover topics that fit within the theme of the library. We show that such scope judgments can be automated using a combination of text classification techniques and topic modeling. Our models address two significant challenges in making scope judgments: only a small number of out-of-scope resources are typically available, and the topic distinctions required for digital libraries are much more subtle than classic text classification problems. To meet these challenges, our models combine support vector machine learners optimized to different performance metrics and semantic topics induced by unsupervised statistical topic models. Our best model is able to distinguish resources that belong in DLESE from resources that don't with an accuracy of around 70\%. We see these models as the first steps towards increasing the scalability of digital libraries and dramatically reducing the workload required to maintain them.}, address = {New York, NY, USA}, author = {Bethard, Steven and Ghosh, Soumya and Martin, James H. and Sumner, Tamara}, booktitle = {JCDL '09: Proceedings of the 2009 joint international conference on Digital libraries}, citeulike-article-id = {5089969}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1555405}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1555400.1555405}, doi = {10.1145/1555400.1555405}, isbn = {978-1-60558-322-8}, keywords = {digital\_libraries, topic-modeling}, location = {Austin, TX, USA}, pages = {19--28}, posted-at = {2009-07-07 20:50:09}, priority = {0}, publisher = {ACM}, title = {Topic model methods for automatically identifying out-of-scope resources}, url = {http://dx.doi.org/10.1145/1555400.1555405}, year = {2009} }

TY - CONF ID - citeulike:5089969 L3 - citeulike-article-id:5089969 N2 - Recent years have seen the rise of subject-themed digital libraries, such as the NSDL pathways and the Digital Library for Earth System Education (DLESE). These libraries often need to manually verify that contributed resources cover topics that fit within the theme of the library. We show that such scope judgments can be automated using a combination of text classification techniques and topic modeling. Our models address two significant challenges in making scope judgments: only a small number of out-of-scope resources are typically available, and the topic distinctions required for digital libraries are much more subtle than classic text classification problems. To meet these challenges, our models combine support vector machine learners optimized to different performance metrics and semantic topics induced by unsupervised statistical topic models. Our best model is able to distinguish resources that belong in DLESE from resources that don't with an accuracy of around 70%. We see these models as the first steps towards increasing the scalability of digital libraries and dramatically reducing the workload required to maintain them. CY - Austin, TX, USA SN - 978-1-60558-322-8 AD - New York, NY, USA EP - 28 TI - Topic model methods for automatically identifying out-of-scope resources PB - ACM T2 - JCDL '09: Proceedings of the 2009 joint international conference on Digital libraries SP - 19 KW - digital_libraries KW - topic-modeling AU - Bethard, Steven AU - Ghosh, Soumya AU - Martin, James AU - Sumner, Tamara PY - 2009/// UR - http://dx.doi.org/10.1145/1555400.1555405 ER -