How to Improve your Twitter Followers Count (Part I)

So far I’ve shared several articles of my work with the Twitter API and my direct personal experience with the platform itself. In 2022, my goal is to really increase my Twitter follower count significantly. It still amazes me to see Twitter accounts with tens of thousands of followers. People who may or may not be known on other platforms have a significant following on Twitter.

Based purely on anecdotal experience, here are the things I believe will increase your Twitter follower count:

  1. Have a high follower count on other platforms (I.e., Instagram, TikTok, Facebook, etc.)
  2. Someone who is very well known finds a tweet you made and retweets it. Like the President or Oprah retweeting one of your tweets.
  3. Be a celebrity, politician or influencer who is in the public.

Okay, let’s say you have none of the things above. I will give you some hints on how you can improve your twitter following (Caveat: All this advice from someone (me) who has very low follower numbers).

You can take a look at my numbers and ask yourself, “Why would I take advice from someone who has low numbers themselves?” I can certainly understand that sentiment. But the reason why you should follow this article series, is that I have been doing some significant research into this and putting a plan in place to increase my followers count. So, if you’re not putting in a strategy yourself, what does it hurt to take a few pointers? I do recommend reading more articles on the topic, however.

Also, another reason to follow this advice is that I have used Machine Learning and Data Science techniques to study this subject. I will be adding more of my research for these articles on Twitter followership soon. But for now, I recommend that you read my current Data Science research including, “Creating Twitter Sentiment Association Analysis using the Association Rules and Recommender System Methods” and Apriori Association Analysis using R. These articles show how to use the Twitter API and R to do Twitter data analysis. In particular, learning about association rules and association analysis to get a idea how to find patterns and relationships between twitter followers and twitter followership and follower retweets. I will soon be presenting visualizations that will expand on this concept of twitter follower counts.

Another article of mine to read is more anecdotal but very important when it comes to taking control of your twitter feed. It’s very easy to get completely absorbed by twitter conversations and comments. To be quite honest with you, Twitter is a very depressing place at times. People who have high twitter follower counts will tweet out misinformation, insults, slurs, racism, sexism, homophobia, etc. and as someone who doesn’t like to perpetuate such things on the internet, you can really feel powerless and helpless to the slew of followers co-signing onto someone’s tweets with comments and retweets and likes. Please read my article on this Twitter is a Social Media Engagement Multiplier about more on this.

So finally, here are the ways an average user can increase their follower count.

  1. TWEET A LOT! I mean a whole lot. Try to get at least two thousand tweets in about six months. Use hash tags always.
  2. If you only want to tweet about specific niche topics such as business, engineering or technology, make sure to follow the most popular accounts and add to the conversation. Retweet popular posts. Most of these topics are very non-toxic and you will find people who are of the same mindset and are objective.
  3. Politics is truly the third rail on Twitter. If you care about this, my recommendation is be prepared to get into depressing twitter battles. And be prepared to stand your ground and go all into it, if you can take it. People are passionate about politics on twitter, and tweeting a lot about it on a daily basis will grow your audience. Follow both people you align with and people you are diametrically opposed to.
  4. Only follow these types of accounts: A) People or enterprises that are popular and newsworthy on Twitter. B) Accounts that have a 1:1 to 4:5 twitter follower to twitter following count. In other words, follow accounts which have as many followers as they are following. Meaning, if you follow them, they are likely to follow you back (See number 5 for the exception to this rule).
  5. The exception to rule 4 is that if it’s a popular or newsworthy account, or an account that represents a business or think tank, it’s important to follow them because it will give you insight to what topics are important on the platform.

Please stay tuned for more insight into this topics in Part 2.

Creating Twitter Sentiment Association Analysis using the Association Rules and Recommender System Methods

Contextual text mining methods extract information from documents, live data streams and social media.  In this project, thousands of tweets by users were extracted to generate  sentiment analysis scores.

Sentiment analysis is a common text classification tool that analyzes streams of text data in order to ascertain the sentiment (subject context) of the text, which is typically classified as positive, negative or neutral. 

In the R sentiment analysis engine, our team built, the sentiment score has a range of .-5 to 5. Numbers within this range determine the the change in sentiment. 


Sentiment Scores are determined by a text file of key words and scores called the AFINN lexicon.  It’s a popular with simple lexicon used in sentiment analysis.  

New versions of the file are released in source repositories and contains over 3,300+ words with scores associated with each word based on its level of positivity or negativity.

Twitter is an excellent example of sentiment analysis.

An example of exploration of the sentiment scores based on the retweets filtered on the keywords:

  1. Trump
  2. Biden
  3. Republican
  4. Democrat
  5. Election

The data was created using a sentiment engine built in R.  It is mostly based on the political climate in the United States leading up to and after the 2020 United States election.

Each bubble size represents the followers of user who’ve retweeted.  The bubble size gives a sense of the influence of those users (impact). The Y-axis is the sentiment score, the X-axis represents the retweet count of the bubble name.

“Impact” is a measure of how often a twitter user is retweeted by users with high follower counts.

Using the Apriori Algorithm, you can build a sentiment association analysis in R. See my article on Apriori Association Analysis in R.

Applying the Apriori algorithm. using the single format, we assigned our transactions as the sentiment score and We assigned items_id as retweeted_screen_name.  

This is the measure the association between highly retweeted accounts and their associations based on sentiment scores (negative, neutral, positive).  Support is the minimum support for an itemset.  Minimum support was set to 0.02.

The majority of the high retweeted accounts had highly confident associations based on sentiment values. We then focused on the highest confidence associates that provided lift above 1.  After removing redundancy, we were able to see the accounts where sentiment values are strongly associated between accounts.

 According to the scatter plot above, we see most of the rules overlap, but have very good lift due to strong associations, but also this is indicated by the limited number of transactions and redundancy in the rules.

The analysis showed a large number of redundancy, but this was mostly due to the near nominal level of sentiment values.  So having high lift, a larger minimum support and .removing redundancy find the most valuable rules.