Welcome to the CSIR-DSFSI-MMZA 2021 Municipal Election Social Media Monitoring Project (ZA Municipal Election 2021 SMMP). To learn more about the project, go to About Project. For all of our analysis, check the analysis posts below.
(Draft - early version) In this post we analyse the data based on the popular hashtags shared throughout the process of collecting Tweets from Twitter which is a well-known social media platform. Here we aim to analyse the data and understand the various popular hashtags shared amongst social media users about elections.
Nov 15, 2021
(Draft - early version) We have spent some of our analysis for this project on looking at users and the content they create. It is important to engage with what users are saying to understand what type of information they are spreading. In this specific post, we will explore the relationship or connection between users, that is, how users interact with each other. To do so, we will look at the network graph associated with users. To do so, we will specifically focus on constructing connections between users based on what they say, especially if they mention one another. We will perform this analysis based on the data we already collected and use the previous examples as a template for the graph analysis. Finally, in this post, we will unpack what insights we can gain from this type of association analysis so that you too may gain insight and value from using this type of an analysis on text you mined.
Nov 12, 2021
This post looks at an unsupervised approach to extracting discussed topics. It is an approach to create a summary of what was discussed within our social media dataset. In our case it also helps in better navigating the data in the pursuit of understanding what misinformation may have been created during the lead up to the 2021 South African Municipal Elections.
Nov 5, 2021
In this post we start with an exploratory analysis based on the user information we have from the social media microblog post data we have mined. In addition to this, we also accessed a BOT evaluation service to get scores for an account on the basis of whether or not the account is likely a social media BOT or a person. This type of exploration is important as we want to understand the actual trends people are spreading about the elections, and not the type of information that is spread through a BOT. **Note:** *This post was updated on 1 March 2022 to take into account removal of retweeted content*
Nov 1, 2021
In this specific post, we will explore what information and contexts are present within our most frequent words and most frequent phrases from the data. To do so, we would need to look into how we obtained the data, how we visualised the information, and use a visualisation technique to illustrate posts from 10 different political parties. **Note:** *This post was updated on 1 March 2022 to take into account removal of retweeted content*
Nov 1, 2021
In this post, we will go through loading our data sets, and checking our sample size as well as combine different data sets. This means that we are going to check what is in our data, and whether or not the data itself will meet our expectations when we perform the analysis. We collected microblog post data using both Twint and Twarc tools in the Python language, and once the information is deemed satisfactory and meets all the requirements, we will combine this data into a single data object for further analysis. **Note:** *This post was updated on 1 March 2022 to take into account removal of retweeted content*
Oct 31, 2021
