@inproceedings{e86bb24f7e7845d7810a1f86b95a1e29,
title = "A Comparative Evaluation of Preprocessing Techniques for Short Texts in Spanish",
abstract = "Natural Language Processing (NLP) is used to identify key information, generating predictive models, and explaining global events or trends. Also, NLP is supported during the process to create knowledge. Therefore, it is important to apply refinement techniques in major stages such as preprocessing, when data is frequently produced and processed with poor results. This document analyzes and measures the impact of combinations of preprocessing techniques and libraries for short texts that have been written in Spanish. These techniques were applied in tweets for analysis of sentiments considering evaluation parameters in its analysis, the processing time and characteristics of the techniques for each library. The performed experimentation provides readers insights for choosing the appropriate combination of techniques during preprocessing. The results show improvement of up to 5\% to 9\% in the performance of the classification.",
keywords = "Natural Language Processing, Preprocessing, Sentiment analysis, Text mining, Twitter",
author = "Marcos Orellana and Andrea Trujillo and Priscila Cedillo",
note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; Future of Information and Communication Conference, FICC 2020 ; Conference date: 05-03-2020 Through 06-03-2020",
year = "2020",
doi = "10.1007/978-3-030-39442-4\_10",
language = "Ingl{\'e}s",
isbn = "9783030394417",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer",
pages = "111--124",
editor = "Kohei Arai and Supriya Kapoor and Rahul Bhatia",
booktitle = "Advances in Information and Communication - Proceedings of the 2020 Future of Information and Communication Conference FICC",
}