Topic identification from news blog in Spanish language.

Currently, exist a large amount of news in a digital format needs to be classified or labeled automatically according to its content. Latent Dirichlet Allocation (LDA) is an unsupervised technique that automatically creates topics based on words in documents. The present work aims to apply LDA in order to analyze and extract topics from digital news in the Spanish language. A total of 198 digital news were collected from a university news blog. A data pre-processing and representation in vector spaces were carried out and k values were selected based on the coherence metric. A term frequency-inverse document frequency (TF_IDF) matrix and a combination of unigrams and bigrams produce topics with a variety of terms and topics related to university activities like study programs, research, projects for innovation, and social responsibility. Furthermore, with the manual validation process, terms in topics correspond with hashtags written by the communication professionals