TY - JOUR AU - Weren, Edson R. D. AU - Kauer, Anderson U. AU - Mizusaki, Lucas AU - Moreira, Viviane P. AU - de Oliveira, J. Palazzo M. AU - Wives, Leandro K. PY - 2014/10/02 Y2 - 2024/03/29 TI - Examining Multiple Features for Author Profiling JF - Journal of Information and Data Management JA - JIDM VL - 5 IS - 3 SE - SBBD Articles DO - 10.5753/jidm.2014.1543 UR - https://sol.sbc.org.br/journals/index.php/jidm/article/view/1543 SP - 266 AB - Authorship analysis aims at classifying texts based on the stylistic choices of their authors. <br />The idea is to discover characteristics of the authors of the texts. <br />This task has a growing importance in forensics, security, and marketing. <br />In this work, we focus on discovering age and gender from blog authors. <br />With this goal in mind, we analyzed a large number of features -- ranging from Information Retrieval to Sentiment Analysis. <br />This paper reports on the usefulness of these features. <br />Experiments on a corpus of over 236K blogs show that a classifier using the features explored here have outperformed the state-of-the art.<br />More importantly, the experiments show that the Information Retrieval features proposed in our work are the most discriminative and yield the best class predictions. ER -