Personality recognition in source code constitutes a novel task in the field of author profiling on written text. In this paper we describe our proposal for the PR-SOCO shared task in FIRE 2016, which is based on a shallow recurrent LSTM neural network that tries to predict five personality traits of the author given a source code fragment. Our preliminary results show that it should be possibl...

This paper describes the organisation and results of RepLab 2014, the third competitive evaluation campaign for Online Reputation Management systems. This year the focus lied on two new tasks: reputation dimensions classification and author profiling, which complement the aspects of reputation analysis studied in the previous campaigns. The participants were asked (1) to classify tweets applyin...

Many methods have been used to recognise author personality traits from text, typically combining linguistic feature engineering with shallow learning models, e.g. linear regression or Support Vector Machines. This work uses deep-learningbased models and atomic features of text – the characters – to build hierarchical, vectorial word and sentence representations for trait inference. This method...

In this paper, we present our approach for profiling Arabic authors on twitter, based their tweets. We consider here the dialect of an author as important trait to be predicted. For purpose, many indicators, feature vectors and machine learning-based classifiers were implemented. The results these compared find out best prediction model. model was obtained using random forest classifier with fu...

Social media provide a rich source of author-identified text that can be used for personality profiling. However, differences in length and number of entries, syntax, abbreviations, spelling and grammar errors, and topics can affect type and difficulty of preprocessing to extract appropriate text, accuracy of training, time period sampling for training texts, and rate of degradation of accuracy...

background: the purpose of this study was to detect the prevalence of ghost and honorary authors and its determinant factors in bio-medical journals of iran. methods: the study was done in 2009-10 in tehran, kerman, and iran medical universities, iran.  we contacted the first or corresponding authors of the papers had published papers in the recent two issues of iranian journal of public health...