Twitter" on Aquaculture: understanding the latent information using R

Abstract

Social network sites such as Facebook and Twitter have significant importance in connecting people at present. For scholarly use, information from these networks can be used for various research purposes including data mining trend analysis etc. On the other hand, aquaculture provides one of the best solutions for global food security and poverty alleviation. Future growth of aquaculture practices may also depend upon the knowledge/information sharing on social media platformi. The purpose of this itudy was to understand the latent information of twitter messages (tweets) related to the aquaculture. R programming language and the TwitteR package were used to extract and analyze the tweets. Topic modeling approach was used to identiff the key aquaculture themes that can be used to classi1r ihe tweets. Descriptive analysis of tweets indicated that twitter users have used 17 language profiles. 372 twitter profiles tweeted about aquaculture. "GAA Aquaculture" (2.2o/o), "Farming Til+ia; $.gVo),,,Grow Aquapincis" (1.60/o), "wild4salmon" (L.2o/o) and "FAo frsh" {L.2o/o) were top twittei profiles with the highest number of tweets. 'Aquaculture', 'salmon', 'fish', 'sustainable' and 'lice' werl most frequent keywords' Correlation analysis indicated that term 'salmon' was significantly correlated (p<0.0S) with 'Wild salmon', 'bute fish', 'Argyll' and 'fish farm get out'. Topic model results indicated that tweets can be classified into five key themes (Food security and sustainable aquaculture, fish nutrition, sea Iice infestation in salmon aquaculture and Tilapia aquaculture). Diurnal variation of the tweets indicated that food security, sustainable aquaculture, fish nutrition and sea lice infestation were most discussed topics among twitter community.