Shallow Recurrent Neural Network for Personality Recognition in Source Code

Doval, Yerai; Gómez-Rodríguez, Carlos; Vilares, Jesús

Use this link to cite:

http://hdl.handle.net/2183/19312

Shallow Recurrent Neural Network for Personality Recognition in Source Code

Files

Doval_Yerai_2016_Shallow_Recurrent_Neural_Network_for_Personality_Recognition_in_Source_Code.pdf (249.34 KB)

Identifiers

URI: http://hdl.handle.net/2183/19312

Publication date

2016-12

Authors

Doval, Yerai

Gómez-Rodríguez, Carlos

Vilares, Jesús

Bibliographic citation

Yerai Doval, Carlos Gómez-Rodríguez and Jesús Vilares, Shallow Recurrent Neural Network for Personality Recognition in Source Code, in Prasenjit Majumder, Mandar Mitra, Parth Mehta, Jainisha Sankhavara and Kripabandhu Ghosh (eds.), Working notes of FIRE 2016 - Forum for Information Retrieval Evaluation, CEUR Workshop Proceedings, Vol. 1737, pp. 33-37, 2016.

Abstract

[Abstract] 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 personalityaits of the author given a source code fragment. Our preliminary results show that it should be possible to tackle the problem at hand with our approach but also that there is still room for improvement through more complex network architectures and training processes