@InProceedings{10.1007/978-3-319-62434-1_2,
author="N{\'u}{\~{n}}ez-Reyes, Alba
and Villatoro-Tello, Esa{\'u}
and Ram{\'i}rez-de-la-Rosa, Gabriela
and S{\'a}nchez-S{\'a}nchez, Christian",
editor="Sidorov, Grigori
and Herrera-Alc{\'a}ntara, Oscar",
title="A Compact Representation for Cross-Domain Short Text Clustering",
booktitle="Advances in Computational Intelligence",
year="2017",
publisher="Springer International Publishing",
address="Cham",
pages="16--26",
abstract="Nowadays, Twitter depicts a rich source of on-line reviews, ratings, recommendations, and other forms of opinion expressions. This scenario has created the compelling demand to develop innovative mechanisms to store, search, organize and analyze all this data automatically. Unfortunately, it is seldom available to have enough labeled data in Twitter, because of the cost of the process or due to the impossibility to obtain them, given the rapid growing and change of this kind of media. To avoid such limitations, unsupervised categorization strategies are employed. In this paper we face the problem of cross-domain short text clustering through a compact representation that allows us to avoid the problems that arise with the high dimensionality and sparseness of vocabulary. Our experiments, conducted on a cross-domain scenario using very short texts, indicate that the proposed representation allows to generate high quality groups, according to the value of Silhouette coefficient obtained.",
isbn="978-3-319-62434-1"
}