Author Profiling Using Support Vector Machines

The objective of this work is to identify the gender and age of the author of a set of tweets using Support Vector Machines. This work is done as a task for the PAN 2016 which is a part of the CLEF conference. Techniques like tagging, removing stopwords, stemming, Bag-of-Words representation were used in order to create a 10 classes model. The tuning of the model was based on grid-search using k-fold cross-validation. The model was tested for precision and recall with the corpus from PAN 2015 and PAN 2016 and the results are presented. We have experienced the Peaking Phenomenon with the increment of the number of features. In the future we plan to try the term frequency-inverse document frequency in order to improve our results.

[1]  Rong Jin,et al.  Understanding bag-of-words model: a statistical framework , 2010, Int. J. Mach. Learn. Cybern..

[2]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[3]  Benno Stein,et al.  TIRA: Configuring, Executing, and Disseminating Information Retrieval Experiments , 2012, 2012 23rd International Workshop on Database and Expert Systems Applications.

[4]  Edward R. Dougherty,et al.  The peaking phenomenon in the presence of feature-selection , 2008, Pattern Recognit. Lett..

[5]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

[6]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[7]  David D. Lewis,et al.  Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval , 1998, ECML.

[8]  Benno Stein,et al.  Overview of the 4th Author Profiling Task at PAN 2016: Cross-Genre Evaluations , 2016, CLEF.

[9]  Benno Stein,et al.  Improving the Reproducibility of PAN's Shared Tasks: - Plagiarism Detection, Author Identification, and Author Profiling , 2014, CLEF.

[10]  Marti A. Hearst.  Trends & Controversies: Support Vector Machines , 1998, IEEE Intell. Syst..

[11]  Brendan T. O'Connor,et al.  Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks , 2008, EMNLP.

[12]  Juan Enrique Ramos,et al.  Using TF-IDF to Determine Word Relevance in Document Queries , 2003 .

[13]  Julie Beth Lovins,et al.  Development of a stemming algorithm , 1968, Mech. Transl. Comput. Linguistics.