Can Twitter Data be Used to Predict Elections?


Can Twitter Data be Used to Predict Elections? | Social Media TodayData is everywhere in the modern world. Almost every interaction touches, in some way, a digital communications medium, meaning it can be tracked, it can be saved and it can be logged for analysis and reference. It’s estimated that more than 90% of the world’s data has been generated in the last two years, with an increasing part of that coming from social networks – there’s so much data that no one could fully understand what it might mean in terms of insights and analytics, and the possibilities of what we might be able to ascertain from such masses of information.

Reports have shown that social media data – Twitter data, specifically – can predict things like flu outbreaks, earthquakes, even stock market fluctuations. But can Twitter data be used to predict the outcome of an election? A range of academic studies have been conducted on this very topic, and while most suggest that Twitter can be used as a solid indicator of election outcomes, there are some provisos built in around the accuracy of voter swings and the relevance of sentiment.

Interestingly, we may have a ready-made test case for this, with Twitter’s Canadian blog this week publishing a listing of stats ahead of the nation’s upcoming federal election. The findings show that Justin Trudeau is clearly in the lead in terms of both mentions and follower growth – but will that mean Trudeau will ultimately win the election? It’s an interesting one to watch – here are the findings thus far.

On the Campaign Trail

From the Twitter Canada blog post:

With 6,000,000+ election-related Tweets sent over the past two-and-a-half months, Canadians have flocked to Twitter to discuss key issues, follow candidate debates and share opinions as the #elxn42 campaign took shape across the nation. By comparison, there were just over 4,000,000 #cdnpoli tweets during the 12 months of 2014.”

That’s a lot of data to work with – given this, there must be some way to glean some level of comparative insights from tweet mentions, right? The conversation around the Canadian election has ramped up over time, with peaks at important junctures in the campaign, as highlighted in this mentions graph.

Can Twitter Data be Used to Predict Elections? | Social Media TodaySo we know when people have been more engaged, and that they have, in fact, been significantly engaged in the election via tweet – but how does that relate to the specific candidates? And what can that show us, in terms of predicting the final outcome?

As noted, Twitter data currently indicates that Justin Trudeau holds a commanding lead in terms of mentions, holding 36% of the share of voice.

Can Twitter Data be Used to Predict Elections? | Social Media TodayAnd Trudeau has also gained the most Twitter followers during the campaign with 94,000+ new additions between August 2 and October 14, 2015. 

Can Twitter Data be Used to Predict Elections? | Social Media TodayWhich would suggest that Trudeau is the one to watch – but, of course, these graphs don’t measure sentiment, which is an important element of any such analysis. The first graph alone, looking at share of voice, could be meaningless, as more mentions doesn’t necessarily mean more popularity, but then the inclusion of the second indicator, follower growth, would suggest that Trudeau is gaining support, which contextualizes those mentions a little more. Even without sentiment, could these two charts, in conjunction, be indicative of the likely outcome on October 19th?

Sentiment and Context

In an article published in The Atlantic in 2012, Alexander Furnas argued that you can’t use Twitter to predict elections because, among other reasons, Twitter is a non-representative sample of people, and political tweeting is also a niche activity, which biases the results.

“It may be possible to model public opinion with Twitter, but it would require a much more sophisticated understanding than we now have about who tweets about politics and why, how their tweets relate to their offline actions, and how they differ from the general voting population. Without high-level mechanisms for accounting for these systemic biases, proper weighting and careful, context sensitive interpretation and analysis election prediction with Twitter is a case of “garbage in, garbage out” data work. “

While that article was published a few years back now, this sentiment is largely indicative of the skepticism around Twitter’s data accuracy, and thus, the ability to use such input as a means to predict polling outcomes. In counter to this, in a study titled “On Using Twitter to Monitor Political Sentiment and Predict Election Results” published by researchers from Dublin City University in 2011, the analysts concluded that Twitter data could be used as an accurate indicator, with tweet volume cited as the key measurable.

“…we observe that volume is the single biggest predictive variable followed by inter-party sentiment. Given sufficient data, intra-party sentiment appears to be less valuable as a predictive measure. Our speculation is that the relative success of the inter-party sentiment is due to the closed nature of the system.”

That research indicated that 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 a given news story or event.

Researchers from Germany came to similar conclusions in 2010:

“The mere number of tweets reflects voter preferences and comes close to traditional election polls, while the sentiment of Twitter messages closely corresponds to political programs, candidate profiles, and evidence from the media coverage of the campaign trail.”

In this sense, the correlation of share of voice and increased following could well be indicative of the pending result in the Canadian election. Is that how it will play out? While it’s only one example, it’s an interesting case study, and one worth considering as we await the results of the Canadian election, which is being held next week.

Social Media Today RSS


Where Are The Landing Pages Used With eMail Marketing?


Unique Different

In the last post, we saw how landing pages work in tandem with email marketing to grow an audience base.

We also discussed how landing pages are different from home pages:

  • In the audience they serve and
  • The objectives they help to achieve

This video that demonstrates how the pages are different:

Landing pages or opt-in pages are tools used to attract visitors who are interested in your content. However, very often, you don’t see too many landing pages on sites that you visit. That is perhaps why, we hear the following:

Recommended for YouWebcast: 4 Steps to Creating a Marketing Content Plan

“But not too many businesses are using landing pages.” and “Are you sure I need one?”

What do you say?

Glad that the question was raised so it can be addressed. And ‘ll let you draw your own conclusion at the end of the post.

“I don’t see many opt in pages or free incentivized giveaways (lead magnets)

You may not see landing pages but they are everywhere.

1. Many businesses use landing pages with opt-in forms

Way back in 1996, Seth Godin taught the importance of permission marketing; that’s requesting for explicit permission before sending valuable follow-up communications to those who value your free giveaways (ebook, free consult or free trial), sometimes referred to as freebies or lead magnets.

Opt-in forms, lead magnets and email marketing, they all work together to offer something of great value to a specific audience group in exchange for the privilege to build a relationship with the audience via a series of emails.

This is with the intention of winning them over for sales further down the road.

Till this day, hundreds of smart marketers and businesses have built (and continue to build) a huge database (with permission) using landing pages.

Companies that offer landing pages templates are sprouting and these include: Unbounce, Lead Pages, Rainmaker to name just a few. We also have business owners and professionals who prefers to design their own landing pages with their designers.

2. Landing pages may not be visible on the main sites, but they are working in the background

For example, this is a landing page, but you won’t see it if you visit the main site.

Not seeing too many landing pages does not follow that these are not used.

Some stream-lined sites may only have 5 or 6 pages and they may have tons of dedicated landing pages and sales pages that work hard for the business behind the scene.

3. The concept of Landing Pages are used in other forms

Another thing to note is that the concept of landing pages have been applied to pop up forms or attention grabbing hello bars.

Pop up forms are forms that pop up from nowhere when you are visiting a page and they specifically ask for your emails. Some people find pop-up forms a little annoying as they appear unexpected and sometimes you are not sure how to close off the box.

Hello bars are more subtle; they are usually across the top of the page, asking for an email address in exchange for some incentives.

Pay attention the next time you visit sites and you’ll see these forms on most web pages of savvy marketers. While they serve the same purpose as landing page, they don’t convert as well because there are other things to distract the visitor.

Having these on a dedicated page (a landing page) removes all distractions and increase the chance of conversion. This infograph shows why this is so.

Lastly the “majority” is not always on the right track

It is a dangerous thing to follow blindly as the majority is not necessarily always doing the right thing.

Early adopters know this very well. By the time a concept is embraced, it is proven to be working and has gone mainstream. That means many people are already using it and you are only just playing catch up.

Trendsetters and early adopters are the minority, refer to Seth Godin’s post here.

Lead magnets and opt-in forms are nothing new. Increasingly, more businesses are starting to see the benefits of using them. But by now, a simple incentive may no be sufficient to be attractive. Trendsetters and early adopters are now using gated sites to grow their following (something for another post).

When too many people are rushing to jump onto the bandwagon, it is time to re-evaluate the situation. Much like the case of the trading in the stock market (no, I don’t trade on the stock market).

Consider yourself fortunate to have this knowledge

So if you think not too many businesses are using email marketing right today, then consider yourself fortunate to have this knowledge. You are now ahead of the many others – provided you implement what you know.

There us not a short cut. email marketing does not provide instantaneous results for those looking for quick results. It takes time to build your database and your online authority. Permission marketing and landing pages are for those interested in building long term sustainable business

Your thoughts?

If you have another question, just send those in as well and we can discuss it together.

Digital & Social Articles on Business 2 Community