Computational methods in authorship attribution Export

@article{citeulike:3452983, abstract = {Statistical authorship attribution has a long history, culminating in the use of modern machine learning classification methods. Nevertheless, most of this work suffers from the limitation of assuming a small closed set of candidate authors and essentially unlimited training text for each. Real-life authorship attribution problems, however, typically fall short of this ideal. Thus, following detailed discussion of previous work, three scenarios are considered here for which solutions to the basic attribution problem are inadequate. In the first variant, the profiling problem, there is no candidate set at all; in this case, the challenge is to provide as much demographic or psychological information as possible about the author. In the second variant, the needle-in-a-haystack problem, there are many thousands of candidates for each of whom we might have a very limited writing sample. In the third variant, the verification problem, there is no closed candidate set but there is one suspect; in this case, the challenge is to determine if the suspect is or is not the author. For each variant, it is shown how machine learning methods can be adapted to handle the special challenges of that variant.}, address = {Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel; Department of Computer Science, Illinois Institute of Technology, 10 W. 31st Street, Chicago, IL 60616}, author = {Koppel, Moshe and Schler, Jonathan and Argamon, Shlomo}, citeulike-article-id = {3452983}, citeulike-linkout-0 = {http://dx.doi.org/10.1002/asi.20961}, citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/121421600/ABSTRACT}, doi = {10.1002/asi.20961}, journal = {Journal of the American Society for Information Science and Technology}, keywords = {authorship\_attribution}, number = {9999}, pages = {NA+}, posted-at = {2009-04-24 18:33:46}, priority = {0}, title = {Computational methods in authorship attribution}, url = {http://dx.doi.org/10.1002/asi.20961}, volume = {9999}, year = {2008} }

TY - JOUR ID - citeulike:3452983 L3 - citeulike-article-id:3452983 N2 - Statistical authorship attribution has a long history, culminating in the use of modern machine learning classification methods. Nevertheless, most of this work suffers from the limitation of assuming a small closed set of candidate authors and essentially unlimited training text for each. Real-life authorship attribution problems, however, typically fall short of this ideal. Thus, following detailed discussion of previous work, three scenarios are considered here for which solutions to the basic attribution problem are inadequate. In the first variant, the profiling problem, there is no candidate set at all; in this case, the challenge is to provide as much demographic or psychological information as possible about the author. In the second variant, the needle-in-a-haystack problem, there are many thousands of candidates for each of whom we might have a very limited writing sample. In the third variant, the verification problem, there is no closed candidate set but there is one suspect; in this case, the challenge is to determine if the suspect is or is not the author. For each variant, it is shown how machine learning methods can be adapted to handle the special challenges of that variant. IS - 9999 JF - Journal of the American Society for Information Science and Technology AD - Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel; Department of Computer Science, Illinois Institute of Technology, 10 W. 31st Street, Chicago, IL 60616 TI - Computational methods in authorship attribution VL - 9999 SP - NA KW - authorship_attribution AU - Koppel, Moshe AU - Schler, Jonathan AU - Argamon, Shlomo PY - 2008/// UR - http://dx.doi.org/10.1002/asi.20961 ER -