Twitter and Obesity

Data Reduction

 

Using an SQL query, we reduced our database of tweets to a more manageable amount. The query consisted of keywords and hashtags relevant to our study, such as “workout” and #foodporn. A bounding box was used to limit our results to the greater Vancouver area.

 

 

54,000 Tweets

SQL

Query

Tweet Database

> 700 million tweets

Getting Close to the Data

 

The next step was reading through the tweets to identify patterns and evaluate our original SQL query.  We identified three main themes: Diet, Lifestyle/Activity, and Appearance.  We removed erroneous terms from our query and added relevant terms.  We then ran the new query on the database to retrieve the tweets we would analyze.

 

Qualitative Coding

 

Qualitative coding involved formally assigning themes and subthemes to tweets using Nvivo. The parent themes we identified were Healthy and Unhealthy, and the subthemes were Diet, Lifestyle/Activity, and Appearance.  Once the tweets were coded, we were able to analyze the distribution of tweets between themes.  Additionally, since each tweet had an latitude and longitude coordinate, we were able to analyze the spatial distribution as well.

 

 

 

 

 

 

 

Healthy

Unhealthy

Lifestyle

/Activity

Diet

Appearance

Lifestyle

/Activity

Diet

Appearance

© YETI Consulting 2015

PDFs:

Full Report   |  Pyschoanalysis