Mangrove Tweets Dataset v1.0 (Sept 2021–Aug 2022)

Overview This dataset includes a collection of tweets in the Indonesian language related to mangroves and marine ecosystems in Indonesia, gathered over one years. It is designed for topic modeling, text mining, and social-environmental analysis, using natural language processing (NLP) techniques. The tweets were filtered using the keyword "Mangrove" and include both text content and publication timestamps. All tweets are in Indonesian and were collected using scraping libraries. Data Collection Summary Dataset Time Period Library Used Total mangrove_dataset_sept 2022_aug 2023.csv 1 Sept 2021 – 31 Aug 2022 Snscrape 27.371 Contents Each record in the dataset contains: Text: The tweet content (in Bahasa Indonesia) Datetime: The timestamp of the tweet (date of publication)