Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/7065
Title: Gender prediction from Tweets with convolutional neural networks: Notebook for PAN at CLEF 2018
Authors: Sezerer, Erhan
Polatbilek, Ozan
Sevgili, Özge
Tekir, Selma
Sezerer, Erhan
Polatbilek, Ozan
Sevgili, Özge
Tekir, Selma
Izmir Institute of Technology. Computer Engineering
Keywords: Neural networks
Convolution
Convolutional Neural Networks
Issue Date: 2018
Publisher: CEUR Workshop Proceedings
Source: Sezerer, E., Polatbilek, O., Sevgili, Ö., and Tekir, S. (2018, 10-14 September). Gender prediction from Tweets with convolutional neural networks: Notebook for PAN at CLEF 2018. In L. Cappellato, N. Ferro, J.-Y. Nie, and L. Soulier (Eds.), paper presented at the 19th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2018, Avignon, France.
Abstract: This paper presents a system1 developed for the author profiling task of PAN at CLEF 2018. The system utilizes style-based features to predict the gender information from the given tweets of each user. These features are automatically extracted by Convolutional Neural Networks (CNN). The system mainly depends on the idea that the informativeness of each tweet is not the same in terms of the gender of a user. Thus, the attention mechanism is included to the CNN outputs in order to discriminate the tweets carrying more information. Our architecture was able to obtain competitive results on three languages provided by the PAN 2018 author profiling challenge with an average accuracy of 75.1% on local runs and 70.23% on the submission run.
Description: 19th Working Notes of CLEF Conference and Labs of the Evaluation Forum, CLEF 2018; Avignon; France; 10 September 2018 through 14 September 2018
URI: http://ceur-ws.org/Vol-2125/paper_116.pdf
http://hdl.handle.net/11147/7065
ISSN: 1613-0073
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
7065.pdfConference Paper334.46 kBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

Page view(s)

12
checked on Aug 4, 2021

Download(s)

4
checked on Aug 4, 2021

Google ScholarTM

Check


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.