A Twitter Dataset on Tweets about People who Got Lost due to Dementia

dataset

posted on 2018-01-16, 04:57 authored by Kelvin KF Tsoi, Nicholas B Chan, Felix CH Chan, Lingling Zhang, Annisa CH Lee, Helen ML Meng

This is the dataset used and analyzed in the paper "How can we Better Use Twitter to find a Person who Got Lost due to Dementia?".

A total of five tables are included.

1. raw_tweets.rds: All tweets that mentioned (i) "Dementia" or "Alzheimer"; and (ii) "Lost" or "Missing", which were crawled from Twitter from April to May 2017.

2. raw_userinfo.rds: The corresponding Twitter user info of Tweets.

3. filtered_tweets.csv: Tweets that were included in the study. Details (age, gender, place, etc.) of the corresponding lost person mentioned in each tweet were appended in this table.

4. filtered_userinfo.csv: The corresponding Twitter user info of Tweets that were included in the study. Occupation (police / media / others) of each user were appended in this table.

5. cleansed_lostcases.csv: A cleansed table that shows several features of the lost cases.