Abstract
This study proposes an improvement to the Insight Centre for Data Analytics algorithm, which identifies the most relevant topics in a corpus of tweets, and allows the construction of search rules for that topic or topics, in order to build a corpus of tweets for analysis. The improvement shows above 14% improvement in Purity and other metrics, and an execution time of 10% compared to Latent Dirichlet Allocation (LDA).
Author supplied keywords
Cite
CITATION STYLE
Martínez, E. D., Fonseca, J. P., González, V. M., Garduño, G., & Huipet, H. H. (2017). Detection of topics and construction of search rules on Twitter. In Communications in Computer and Information Science (Vol. 735, pp. 171–183). Springer Verlag. https://doi.org/10.1007/978-3-319-66562-7_13
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
