%0 Journal Article %1 ElenaErosheva04062004 %A Erosheva, Elena %A Fienberg, Stephen %A Lafferty, John %D 2004 %J Proceedings of the National Academy of Sciences %K machinelearning model topic %N suppl. 1 %P 5220-5227 %R 10.1073/pnas.0307760101 %T Mixed-membership models of scientific publications %U http://www.pnas.org/cgi/content/abstract/101/suppl_1/5220 %V 101 %X PNAS is one of world's most cited multidisciplinary scientific journals. The PNAS official classification structure of subjects is reflected in topic labels submitted by the authors of articles, largely related to traditionally established disciplines. These include broad field classifications into physical sciences, biological sciences, social sciences, and further subtopic classifications within the fields. Focusing on biological sciences, we explore an internal soft-classification structure of articles based only on semantic decompositions of abstracts and bibliographies and compare it with the formal discipline classifications. Our model assumes that there is a fixed number of internal categories, each characterized by multinomial distributions over words (in abstracts) and references (in bibliographies). Soft classification for each article is based on proportions of the article's content coming from each category. We discuss the appropriateness of the model for the PNAS database as well as other features of the data relevant to soft classification.

@article{ElenaErosheva04062004, abstract = {PNAS is one of world's most cited multidisciplinary scientific journals. The PNAS official classification structure of subjects is reflected in topic labels submitted by the authors of articles, largely related to traditionally established disciplines. These include broad field classifications into physical sciences, biological sciences, social sciences, and further subtopic classifications within the fields. Focusing on biological sciences, we explore an internal soft-classification structure of articles based only on semantic decompositions of abstracts and bibliographies and compare it with the formal discipline classifications. Our model assumes that there is a fixed number of internal categories, each characterized by multinomial distributions over words (in abstracts) and references (in bibliographies). Soft classification for each article is based on proportions of the article's content coming from each category. We discuss the appropriateness of the model for the PNAS database as well as other features of the data relevant to soft classification. }, added-at = {2008-09-09T05:03:35.000+0200}, author = {Erosheva, Elena and Fienberg, Stephen and Lafferty, John}, biburl = {https://www.bibsonomy.org/bibtex/22f54b1b1364ef2225606d30926d6a1f4/tberg}, description = {Mixed-membership models of scientific publications -- Erosheva et al. 101 (Supplement 1): 5220 -- Proceedings of the National Academy of Sciences}, doi = {10.1073/pnas.0307760101}, eprint = {http://www.pnas.org/cgi/reprint/101/suppl_1/5220.pdf}, interhash = {bf8ec74595ae308881b84fd16cee6f6b}, intrahash = {2f54b1b1364ef2225606d30926d6a1f4}, journal = {Proceedings of the National Academy of Sciences}, keywords = {machinelearning model topic}, number = {suppl. 1}, pages = {5220-5227}, timestamp = {2008-09-09T05:03:35.000+0200}, title = {{Mixed-membership models of scientific publications}}, url = {http://www.pnas.org/cgi/content/abstract/101/suppl_1/5220}, volume = 101, year = 2004 }