Marijuana Twitter Analytics: A Terminological Analysis

Introduction: Twitter is rich in data for text and data analytics research. With the ability to capture trends, researchers are able to evaluate the sentiment (i.e. positive (1), neutral (0), or negative (-1)) behind the messages and content for themes. To our knowledge, little research has explored...

Full description

Saved in:
Bibliographic Details
Published in:The journal of the Canadian Health Libraries Association 2020-01, Vol.41 (3), p.147-148
Main Authors: Kung, Janice, Shiri, All, Ly, Kynan
Format: Article
Language:English
Subjects:
Health sciences
Marijuana
Perceptions
Social networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Introduction: Twitter is rich in data for text and data analytics research. With the ability to capture trends, researchers are able to evaluate the sentiment (i.e. positive (1), neutral (0), or negative (-1)) behind the messages and content for themes. To our knowledge, little research has explored terminology use, conversations, and public perceptions of marijuana legalization as reflected on Twitter in a Canadian context. With the recent legalization of marijuana in Canada, this topic is particularly timely and relevant. Methods: Building on previous Twitter analytics studies, we used Twitter API to extract a subset of tweets using relevant hashtags such as #CannabisAct. Using open source programming tools, we analyzed the sampled tweets between September to November 2018 to identify themes, frequently used terms, and co-occurring terms and topics. Results: We collected more than 1,176,000 tweets. The most popular hashtag cooccurrence, two hashtags appearing together, was #cannabis and #cdnpoli. There was a high variance in the sentiment analysis of all collected tweets with the median and mode values of zero (neutral sentiment). Other results will also be shared. Discussion: Using the project as a case study, participants have an opportunity to reflect on possible text-mining applications relevant to health sciences research or to help make informed decisions such as understanding public perceptions about marijuana with a public health lens. Examining and identifying all possible terminologies used by the public could also help inform systematic reviews and other comprehensive searching projects in health sciences and other disciplines.
ISSN:1708-6892