Summarization algorithms performance for topic clustered twitter microblogs

• Main Author: SANTOS, JOHN SIXTO G.
• Format: text
• Published: Archīum Ateneo 2018
• Subjects: Twitter; Corpora (Linguistics) > Data processing; Natural language processing (Computer science); Cluster analysis > Computer programs.
• Online Access: https://archium.ateneo.edu/theses-dissertations/185; http://rizalls.lib.admu.edu.ph/#section=resource&resourceid=1564945654&currentIndex=0&view=fullDetailsDetailsTab
• Institution: Ateneo De Manila University

This paper discusses an approach that would allow for the condensation of a bodyof Twitter microblogs into a wieldy size by extracting the topics being discussed in acorpus of tweets using Latent Dirichlet Allocation (LDA). The approach presents theoutput into a human readable summary using the Phrase Reinforcement (PR)algorithm. The average F-measure score of this method exceeds those of othermethods when evaluated against human-made summaries. Results also suggest thatLDA together with PR is more robust against noisier datasets than the other testedmethods. This solution would help utilize Twitter into a tool not only for sharing ofexperiences but also a tool for gathering the state of the population. Decision makerscan use this solution to make informed action.