Text Analytics Reveals Potential French Election Upset

Tom H. C. Anderson
May 3rd, 2017
Text Analytics Poll Shows Le Pen Positioned to “Trump” Macron

To Americans following the French Presidential Election taking place in less than a week, it might appear as though recent history is repeating itself. And in many ways, it is.

Late last week we ran a Text Analytics Poll™ in France, and the results of our analysis bear a striking resemblance to those of an identical poll we ran in the US just a couple of days prior to the November 8 presidential election.

You may recall that in November, just a day before the US Presidential Election, we posted on this blog results from a Text Analytics Poll™ indicating that Hillary Clinton had a major positioning problem that could cost her the election, in contrast to conventional pollsters’ predictions that had almost universally and, it turns out, incorrectly forecast her winning by a sizable Electoral College margin.

Well, as was the case in our US poll, actual comment data from French respondents in their own words indicates a much, much closer race between Emmanuel Macron and Marine Le Pen than the 60/40 split pollsters have thus far predicted.

In fact, as of Sunday night when we closed this poll—exactly one week before the May 7 runoff election—Marine Le Pen looked a lot like Donald Trump.

About this Text Analytics Poll™

For this French election Text Analytics Poll™, we replicated our November US election poll, taking a French general population sample of 3,000, splitting it in half randomly, and asking each half the same single question, substituting only the candidate’s name:

“Without looking, off the top of your mind, what issues does [insert candidate name] stand for?”

We then machine-translated the responses and analyzed them using the patented OdinText software platform, which identified and quantified potentially important themes/ideas/topics in people’s comments and also qualified and quantified the emotions expressed in those comments.

We use this approach because we’ve found time and again that conventional quantitative survey questions—the sort used in political polls—are usually not terrific predictors of actual behavior.

We know that consumers (and, yes, voters) are generally not rational decision-makers; people rely on emotions and heuristics to make most of our decisions. Ergo, if I really want to understand what will drive actual behavior, the surest way to find out is by allowing you to tell me unaided, in your own words, off the top of your head. Oftentimes, we can accomplish this with one, well-designed question!

French Election Outsider vs. Reformer

Much as we saw in the US race, the French electorate appears to be in a decidedly anti-establishment mood. So it’s no surprise under the circumstances that both of the final contenders in the French presidential runoff could accurately be described as “outsiders,” but what voters may really be after is a reformer.

Bernie Sanders and Donald Trump were both considered outsiders and reformers, although unlike Trump, who successfully hijacked the Republican nomination, Sanders failed to pull off a similar grassroots coup in the Democratic primary. As a result, US voters were faced with a choice between a reformer/outsider and an establishment candidate.

Le Pen has been a member of the French Parliament for more than a decade and she held elected office at the regional level before that. She’s also the scion of a famous political family and, more importantly, the former president of a prominent, albeit right wing, political party, the National Front (FN). Le Pen’s relative “outsider” status stems from the fact that the FN has historically promoted a nationalist agenda and was until recently viewed as outside of the political mainstream (and outside the two major coalitions that have alternated between control of the French government for the last 30-plus years).

Emmanuel Macron, too, is a relative outsider. He’s a former Minister of the Economy and founded the “En Marche”(“Forward!”) political movement in 2016, but he has never held elected office and, as of our poll, remains something of a mystery to potential French voters save for the fact that it’s well known that he made a fortune in investment banking.

Whatever you think of her politics, Le Pen clearly qualifies as a reformer, whereas Macron, while an outsider, appears to have a positioning problem around reform. Let’s take a closer look…

It’s All About Brand Positioning… Again

Whether you’re a corporation or a candidate for office, properly positioning your brand in the mind of your target is arguably the single most important part of the marketing process.

As I noted, our US poll back in November strongly suggested that Hillary Clinton was in more trouble than any of the other polling data to that point had indicated, and the problem was one of positioning relative to the competition.


– The #1 most popular response for Hillary Clinton involved the perception of dishonesty/corruption.

– The #1 and #2 most popular responses for Donald Trump related to platform (immigration, followed by pro-USA/America First), followed thirdly by perceived racism/hatemongering.

Again, I’ll emphasize that these responses were not selected from a list of possible choices, but top-of-mind and unaided from voters in their own words.

What the comment data revealed was that Donald Trump’s campaign messaging was very focused around a two issues—immigration and protectionism—and had been effective in galvanizing voters to whom these positions appealed; Hillary Clinton’s messaging was relatively scattered across a variety of issues, and therefor diluted, which made it difficult for voters to identify her with a key issue they could rally around.

And while an alarmingly high proportion of responses to our question were for both candidates emotionally-charged character attacks, the negative emotional disposition toward Hillary Clinton was actually higher than for Donald Trump. In other words, the dislike among people who disliked Hillary Clinton outweighed the dislike among people who disliked Donald Trump. This probably had little to do with Trump campaign messaging—although they certainly capitalized on it—and was more a reflection of the fact that Hillary Clinton had been highly visible and active in national politics for decades and was already positioned in the minds of voters.

How does this relate to what we see in the French Election data?

The chart below depicts responses from the French to our single question after being analyzed by OdinText and sorted by prevalence of topics/themes (coded red for Macron and blue for Le Pen).

First, it’s important to note that there are inherently fewer issues with which politicians can differentiate themselves in French politics than there are in US politics. For example, issues like abortion, education, healthcare, gun ownership, etc., in France are not hotly contested as they are in the States.

In France—like most European countries in the post-Brexit era—political debate centers primarily around economics internally and in relation to other countries (i.e. the EU), security, and, importantly, immigration.

Here, Le Pen’s positioning is unmistakable, as she was frequently associated with immigration, which works in her favor among those who view immigration as a problem. The issue is tied to security, as well, and given the 2015 Paris attacks, the heightened fear about terrorism coupled with domestic economic concerns could lead voters who might have been historically more sympathetic to pro-immigration platforms to actually vote for Le Pen.

That said, like Hillary Clinton, Marine Le Pen is well known to the French, and already positioned in their eyes. Although she has taken steps to soften the perception, respondents to our poll most frequently said she stands for racism/hate/xenophobia, which does not bode well for her candidacy in socially liberal France.

Macron, by contrast, remains a relative enigma to the French people. Almost twice as many French people said they aren’t sure what Macron stands for compared to Le Pen. In fact, Macron is not tied to any standout platform or issue of importance to the French, whereas Le Pen is positioned as a reformer on immigration to an electorate that, again, is not enamored with the status quo.

Moreover, respondents most frequently associated Macron with “liberalism,” followed by capitalism, which are nearly the same. Indeed, I put liberalism in quotes here to make a very important distinction that might have otherwise been lost on Americans who are not familiar with French politics: Liberalism in France actually refers to economic liberalism favoring free markets—almost the opposite of how the term is used in US politics!

Neither liberalism nor capitalism are necessarily assets in terms of positioning in French politics, particularly for a wealthy investment banker at a time when job security is a major concern among voters. Macron has campaigned as a centrist, stating emphatically that ideologically he is neither left nor right, but our data suggests that he is positioned in the minds of the French as something of a neo-conservative and perhaps an elite. Indeed, the Le Pen campaign has been feeding this positioning and tying it to fears about globalization undermining the economic security of the French people.

We do see in the data that Le Pen’s positioning of Macron as a capitalist “sell-out” and instrument of status quo globalists has achieved some success, but it may be too little too late. While 7.8% of the French in our poll view Macron as capitalist/money man, nearly twice as many describe Le Pen as a hatemongering racist (15.3%).

Ironically, we noted in our US poll that Donald Trump was also described as a racist by more than 10% of Americans just days before the election; however, more than 12% of Americans said that Hillary Clinton was dishonest/“crooked.”

The combined chart below shows how both the French and the American candidates appeared in the eyes of respondents from their respective countries. (Again, note that “liberal” for Macron does not mean fiscal or socially liberal as it does in the context of US politics, but refers to free-market economic liberalism.)

French Election 4

Final Analysis

This upcoming election is actually runoff, and the opponents have basically two weeks to position one another. To this point, the job of defining one’s opponent was much trickier because there were five candidates in the race. In US politics, obviously, candidates have a lot more time to cement positioning against a single opponent.

But French campaign strategists are accustomed to operating within this short timeline. The Macron campaign has enjoyed an advantage in that negative positioning around Le Pen was already firmly in place, whereas Macron was relatively unknown. Conversely, the Le Pen campaign now has a huge opportunity to negatively position Macron as an instrument of global bankers and the status quo and to sway voters with a message of protectionism and security at a time when both have high appeal.

The wild card here is the EU. An EU “Frexit” is generally accepted to be less appealing among the majority of French, and although Le Pen has been softening her rhetoric, she is known to strongly favor leaving the EU. Macron, however, is most assuredly opposed to a Frexit, and the data show that respondents understand this difference.

Much like we saw in the US election results foreshadowed by our own polling data, a victory in this election may not so much amount to an endorsement of one candidate as a rejection of the status quo. And of the two candidates, Le Pen is better positioned as the reformer. She could yet ride a wave of populism that Macron is not equipped to tap into.

In short, do not be surprised if Marine Le Pen pulls off a Trump-style upset in the French Presidential Election. The data strongly suggest she is positioned to do so!


*Note: n=3,000 responses were collected via Google Surveys 4/24-4/30 2017. Google Surveys allow researchers to reach a validated French General Population Representative sample by intercepting people attempting to access high-quality online content or who have downloaded the Google Opinion Rewards mobile app. Results are +/- 2.51% accurate at the 95% confidence interval.

Text Analytics Tips

About Tom H. C. Anderson

Tom H. C. Anderson is the founder and managing partner of OdinText, a venture-backed firm based in Stamford, CT whose eponymous, patented SAS platform is used by Fortune 500 companies like Disney, Coca-Cola and Shell Oil to mine insights from complex, unstructured and mixed data. A recognized authority and pioneer in the field of text analytics with more than two decades of experience in market research, Anderson is the recipient of numerous awards for innovation from industry associations such as CASRO, ESOMAR and the ARF. He was named one of the “Four under 40” market research leaders by the American Marketing Association in 2010. He tweets under the handle @tomhcanderson.

32 thoughts on “Text Analytics Reveals Potential French Election Upset”

  1. Hi Tom,
    Good luck with this. I don’t concur with your assessment, but we’ll see. One issue is the omission in the question set regarding Brexit and French views of the wisdom of what Britain did. The French who view the Brits as making an error won’t want to repeat it, and LePen is linked to the French version of Brexit. Another issue is the original election. The conservative and moderate vote was split between several candidates, and most of those voters can be expected to coalesce around Macron. They were always closer to Macron than LePen on the issues.

  2. Vic, agree completely. The stance on EU is a key factor here, and it seems as if the French are more bullish on EU than Brits. Completely agree that a second comment question here about how French view the EU would add valuable predictive information and we can certainly do the same analysis of that data and add it to this one.

  3. Nicely done, Tom!

    Sometimes the mass media just don’t get it and often exhibits biased or wishful thinking. It will be interesting to see what happens.

  4. I’m torn between hoping against the outcome you suggest and wanting to see your analysis proved right … either way, asking fewer questions has to be the way forward. Good blog post.

  5. Confused as to whether “Anger” points to Victory or defeat, No matter who anyone would predicted as the victor in the recent US Presidential election, they were right-just need to point out which of the two measures you were predicting-popular vote or electoral tally, Wish all betting offered such a guarantee. Cool chart though.

  6. Anger is not good of course, but so is not standing for anything. The question is whether in the short time available, Macron can be painted as a status quo pawn of the investment bank capitalists, if so we’ll see a Trump repeat.

  7. 🙂 Actually, this provided some clarity to some things I suspected. But I have felt the binary choice favours Le Pen, and the clarity of her as a candidate.

  8. Hey Tom,

    Are you going to the Insights and Innovation conference in Atlanta? I would sure love to connect. I, too, predicted the Trump upset. In a far less expert way than you did. I have a few things going on that would benefit from your brainiac ways.

  9. Thank Sarah, yes I too will be at IIEX.

    Will be speaking at Insights Associaiton’s NEXT event in NYC next Tuesday also, but assume you won’t be there?

    look forward to seeing you in Atlanta!

  10. BTW, Sarah, this doesn’t take any brains , the software (OdinText) does all the hard work. You too could do this same analysis for any brands. Heck I can’t even speak French 😉

  11. Being French myself, I loved your post and the methodology – well done Tom !

  12. Being French myself, I loved your post and methodology – well done, Tom !

  13. Very interesting! I wonder if the results have changed given yesterday’s debate that, according to media reports, appears to have been “won” by Macron. That is similar to media analysis here in the US that considered Sec. Clinton the debates “winner.” If Le Pen wins, we should also expect to see media soul-searching similar to what is happening here.

    One difference between France and USA, IIRC, is that the last debate in the US elections was further in advance of the polling date. Plus, wasn’t there the FBI and Wikileaks disclosures just prior to your analysis?

    Would love to see the (translation of) the survey. Thanks for posting this.

  14. What this TextAnalytics Poll answers is the positioning of the candidates. Its almost easier for respondents to answer how a brand or person is positioned, what they stand for, than to decide how they are going to buy or vote in this case. Then there are all sorts of other biases that come into play in answering the latter question which we don’t have here.
    Seeing only parts of the debate it didn’t look to me like Macon was the winner. Specifically the quote by Le Pen about a woman will be running France either way (see video snippet here via this tweet (https://twitter.com/ANOMALY1/status/859933455882366976) was probably the winning quote IMHO.
    But, its true, Macron doesn’t have the baggage that Clinton had so there isn’t as much anger for him. It’s this negative painting of Macron that Le Pen is trying to do in a very short period of time. If she does paint him successfully as a capitalist pawn then she can Trump him, if not, her baggage will cause people to vote for him. The EU here is the only additional factor that didn’t come up as much as I thought it would in the comments, but which I think could be explored more, perhaps in a second Text Analytics Poll 😉

  15. PS. You asked about the survey question. It was:
    “Spontanément, quelles sont, selon vous, les positions et les valeurs défendues par Emmanuel Macron et le mouvement En Marche?”
    “Spontanément, quelles sont, selon vous, les positions et les valeurs défendues par Marine Le Pen et le rassemblement Bleu Marine?”
    For each candidate respectively.

  16. Tom — excellent blog post. The NY Times wrote an article about monitoring social around June 23 2016 that discuss the same trends based on social media conversation analysis. This is fascinating. I am writing an article for our Journal on this topic — would you be willing to be interviewed? Thanks.

  17. My few cents.

    There is a clear commonality between France and the US, culturally, with lifestyle choices (albeit aspirational), and geography. Bear with me. France, like the US, has everything ‘global’ that you need to enjoy life – different weather climates, beaches (nice ones), mountains (really nice ones), well-established and successful urban and rural regions, etc. My point is that for most French nationals/residents they don’t need to leave their country to enjoy the vast array of experiences that most of us need to do, to experience the ‘stuff’ we cannot do at home. Over the past few years new technology has allowed people to travel more cost-efficiently, leave their own country and experience other things, but the French don’t need to, at all. France has everything, so why leave? This has driven, in my opinion, the central argument that the French population really don’t care about anyone else, are happy to nationalist and stay right at home, and have no desire for others to, at least perceptually, take this away (think immigration). Hence, the fierce patriotic sentiment. However, is this sentiment nationalist, patriotic, or separatist? Are there any difference, or similarities in these positions, and to what extent does fine-tuning the respective political parties brand positioning matter? As researchers how do we best determine these insights and more importantly, apply them? Even if Le Pen loses with 40%, that’s a HUGE win for patriotism. It’s not so much Make America Great Again, as Make France “Only”.

  18. I predict that your prediction does not look very good on May 8. It may be several percentage points closer than the polls, but that won’t be nearly enough

  19. Keith, it’s been ages, how have you been, good I hope?
    Obviously a 20 point lead in a popular vote situation makes Macron the favorite. The point of this analysis is the positioning, and the fact that Le Pen looks almost exactly like Trump did before the election.
    What looks different here though is Macron compared to Hillary. He is not as disliked as Hillary. This is where the unknown comes in, and time. The opportunity, or fear, is that this unkown Macron can be positioned by Le Pen as a negative.
    I think we’ve seen some attempts to make him look like a capitalist stooge. But yes the GOP had a lot longer to make Clinton look bad.

  20. The point of this post like all our text analytics tips are to do quick, cheap, sometimes iterative, experiments to showcase just how many ways text analytics can be used. In this case we are showcasing how much can be gathered from 1 single question, fielded for just $300 in 3 days, with an analysis that literally took probably 30 minutes or so (writing up the blog copy took a little longer). Additionally it’s also an experiment in usefulness of machine translation. The 3,000 French comments were analyzed in 2 seconds (I don’t speak French).
    Yet of course, data lined up rather nicely with the same exact experiment we ran just 2 days before US election in English. The same time that Nate Silver was getting crap for an ever so less likely chance of Hillary winning compared to the pollsters. Those results were clearer to me than these, in that Hillary had a true problem. These are similar but different… Do you think Macron will win by more than 20 points?

  21. Hats off to you for having the guts to write this. I just really hope you are wrong!

  22. Well… IPSOS was bang on for the first round of the elections, quite impressive actually. So we shouldn’t be that far off. And we’re talking 20 point difference, which would place the predicted win way outside the margin of error, unlike US where we were pretty much still within the margin of error ( 48 Clinton / 44 Trump on Nov 8 – BBC poll). Additionally, one thing to maybe take into account is that French polling traditionally weights for people to refuse to say they vote for Le Pen, something the US don’t do because they never had to, in polarizing election, this can be an important difference?

  23. Completely agree, people said I was mad when I had trump to win. The media hides the truth on so many occasions. Even after the email dump yesterday. Macron goes into 1/10 favourite while le pen sits at 6/1. (Bookies odds). It is much much closer than that. I hope we are right again for the simple fact that the media will stop giving out false information. If the public knew how close it was they would never have voted Brexit or Trump. Interesting yet worrying times.

  24. Emmett Higgins, i don’t know about Brexit,, but if public knew how close US was they’d still vote for Trump, his anti-Hillary following was/is fanatical. If HRC knew would she have campaigned differently , would she have changed PA or MI? We’ll never know
    In this French study, the results don’t reflect the last debate or the Macron email hack–hopefully the mainstream polls are correct.

  25. ‘Michael’, I assume you don’t have any issue with the positioning as it was described in the data above?
    I’m happy to see that clearly Le Pen wasn’t able to pull a Trump here in less than two weeks, though the possibility was there. Not sure how email leak combines with press freeze affected things, no none could have predicted that of course.
    That said, there is a larger reason I think we saw what we saw here. It’s in the original data as well, but I hope to get a blog post together tomorrow to explain it in more detail, hopefully sharing some additional brand new data at the same time.

  26. I can’t help but wonder how French nationalism reacted to the Russian hacking in their country after beginning to see the extent of Russian interference in the US. The results of the election clearly went to Macron. Tom any chance of a follow-up survey? Again, an open-ended one question survey, perhaps asking why they voted as they did?

Comments are closed.