Source 1:

Social Media and 2016 US election between Hillary Clinton and Donald Trump

Using Social Media Data to Predict to 2016 US Presidential Election

Andrew Hutchinson

May 15, 2016 (BEFORE THE 2016 ELECTION)

...[A] social experiment is to analyze whether social media insights can show us who's going to win an election.

The Popular Vote

The first measure you might look to utilize in a predictive model for an election would be overall mention volume - if a candidate's getting mentioned alot, that's a good sign their message is resonating - or at the least, their voice is reaching a lot of people...a study Dublin City University in 2011 found that tweet volume was "the single biggest predictive variable" in election results, based on their analysis of political sentiment and prediction modeling.

Their research indicated that mention volume was a more accurate indicator than sentiment because volume better represents the relative popularity among the population, while sentiment can be reactive and influenced by responses to

specific news stories or events.

If you were to go with this, as the most basic and simple metric predictor, tweet volume suggest Donald Trump is on a path to The White House.

Appreciating Sentiment

Automated sentiment detection is a minefield, in terms of accuracy. One of the biggest knocks against automated sentiment analysis is that it can't predict sarcasm, which can unfairly skew the results - and this is, no doubt, a significant consideration in the case of Trump. ....what does the data say about the two leading candidates in the current US Presidential campaign?

Using a basic polling tool called HappyGrumpy, we can see that overall sentiment for Donald Trump is actually considered quite positive.

Gaining Support

So if automated sentiment can't provide a definitive qualifier, then what can?

Another measure to consider is follower growth - the combination of mention volume and follower growth in the lead-up to the most recent Canadian election correctly indicated that Justin Trudeau would emerge triumphant.

Using Twitter Counter, we can see that Trump has gained 595,777 followers over the last month.

Hillary Clinton, meanwhile, has gained 285, 541 followers in that same time frame.

Source: https://www.socialmediatoday.com/technology-data/using-social-media-data-predict-2016-us-presidential-election

Source 2:

Social Media and 2020 US election between Joe Biden and Donald Trump

Trump, Biden fight for primacy on social media platforms

July 5, 2020

...On Twitter, Trump's 82.4 million followers dwarf Biden's 6.4 million. The president has spent years cultivating a ragtag digital "army" of meme makers and political influencers who retweet campaign messages hundreds of times daily. ... Biden and his allies are now working feverishly to establish a social media force of their own.

For the first time, Biden outspent Trump on Facebook advertising in June, pouring twice as much money into the platform as the president. His campaign is recruiting Instagram supporters to hold virtual fundraisers.

...But Trump's unimpeded access to the digital microphone is facing its limits.

Twitter is beginning to fact check Trump's posts, including one that made unfounded claims that mail-in voting would lead to fraud. The company also alerted users when the president posted a manipulated video, and it hid his Twitter threat about shooting looters in Minneapolis.

..."If you want to compare the attention and engagement metrics, it might look like Trump is way ahead, but that attention and outrage isn't always good," Mercieca said. "When a child is throwing a tantrum, you're giving them attention, but it's not because you approve of their behavior."

Indeed, the Biden campaign argues that despite being outmatched on social media, their engagement is strong.

"The way that they treat their supporters, it's about distraction. It's about keeping them angry," said Rob Friedlander, Biden campaign digital director. "For us it's about, how do we make you feel like you're brought into the campaign."....

Source: https://www.kusi.com/trump-biden-fight-for-primacy-on-social-media-platforms/

Activity 2: Individual Case

Q1: Sentiment Analysis (200 words)

Using examples from the articles above, and the sentiment analysis lectures, discuss how sentiment analysis can give your candidate's election campaign a competitive edge.

Discuss how sentiment analysis can be used to support your candidate's campaign and undermine your opponent's campaign.

Place your response in the space below:

7.5 marks

Q2: Data / Insights Mining 200 words)

Using examples from the articles above, and the insights mining lectures, discuss how data and insights mining can give your candidate's election campaign a competitive edge.

Discuss how data and insights mining can help to identify trends and characteristics that may escape the attention and awareness of human analysts.

Place your response in the space below:

7.5 marks

Q3: Ethics (200 words)

Your firm has been engaged to develop a tweet-bot for your client - either Hillary or Trump. The tweet bot will data mine tweets associated with your candidate, their opponent and everyone else who engages with these people in the form of likes, mentions, retweets and replies.

The tweet bot will then use natural language processing and latent semantic analysis to learn the way your candidate 'speaks'. Once trained, the tweet bot will tweet on your client's behalf so that it sounds like the tweet came from the candidate.

Discuss the ethical considerations involved in the development of this bot. Your response need to address the Laws of Robotics outlined in the Appendix (see last page)

Place your response in the space below: