Last week, Rishi Sunak spent much of the ITV leadership debate repeating his claim that Labour would increase taxes by £2,000. He then subsequently spent much of the weekend apologising for leaving D-Day commemorations early.
The prime minister will have hoped that one of these cut through with voters, but not the other. Did either?
New technology and innovation from YouGov can help us get answers. We have developed a tracker using an in-house large language AI model which allows us to capture and model people’s written responses to the question: ‘Thinking back over the past week, which news story did you hear about the most?’.
This tool uses artificial intelligence to identify which single recent news story has resonated the most for individual respondents, which we can then aggregate into a nationwide ‘cut through’ report.
As parties start releasing their manifestos this week, YouGov will be publishing regular reports of the news story that is cutting through the most among the British public, offering in-depth, fast and innovative political analytical insights. Today, we are delighted to share some highlights of our first four measurements of topic cut through.
5-6 June
Our first survey, conducted on Wednesday evening through to Thursday morning, saw the top slot occupied by the 21% of Britons whose biggest recollection from the news was that the election was happening in a general sense. They are followed in second place by 12% who noticed the ITV leadership debate specifically, and for a further 6% Rishi Sunak’s £2,000 Labour tax message had been the news item that cut through to them the most (the fifth ‘most noticed’ story).
For one in nine Britons (11%) the fact that Nigel Farage had announced that he would stand for Reform UK (or that he got covered in milkshake shortly after doing so) was the most memorable news event that day, while 7% had most noticed stories about the coming D-Day commemoration.
6-7 June
News about the 80th D-Day anniversary managed to push election coverage from the top spot, with 18% of people saying that the former was the news story they noticed most compared to 16% for the latter.
Otherwise, no new stories had emerged with significant cut through – a near identical 12% say they had most noticed Farage’s return to the political frontline, 11% cited the ITV debate and 8% said that Rishi Sunak’s £2,000 Labour tax claim was the story they most heard about.
With news emerging later in the day about Rishi Sunak ducking out of the D-Day commemorations early to do an interview, we see that 1% had most noticed this story by this point…
7-8 June
…with cut-through becoming more significant on the following day. One in nine Britons (11%) said that Sunak’s D-Day blunder was the news story they most noticed that day, the third highest on the list.
News about the D-Day commemorations themselves continued to hold the top spot at 17%, and general news about the election campaign was most noticed by the second largest number of people, at 16%.
Even as he began to suffer for his D-Day decision, Rishi Sunak may still be pleased to hear that his £2,000 Labour tax claims were still the news story that had the fourth highest cut-through level that day, with 8% saying it was the story they noticed most.
Moving away to a non-political example, we can see that the disappearance of TV doctor Michael Mosley – having been prominently featured by news outlets from 6 June onwards – was the biggest story for 5% of Britons.
10-11 June
After a fieldwork hiatus of a few days, we can see that the disappearance and circumstances of Michael Mosley's death have cut through much further into the public consciousness. Our latest survey finds that fully 30% of Britons now say that Dr Mosley's death is the news story they have heard most about.
The results also show that Rishi Sunak's D-Day woes continued to cut through, with 26% of people saying this was the story they noticed most - the second highest from the list.
Other news has been sidelined by the main two stories. Third place goes to the election campaign in general, at 10%, and the D-Day anniversary more generally is now only cited by 5% of people as their most-noticed story.
What is topic modelling?
Our cut-through tracker uses topic modelling to analyse our open text responses. Topic modelling is a text analysis tool that systematically identifies recurring themes in a collection of texts. Commonly used in natural language processing, topic models typically employ complex probabilistic models or matrix factorisation to analyse the relationships between words. More recently though, a new type of topic model has emerged, one that taps into neural networks and machine learning (otherwise known as AI).
These new methods are particularly useful, as they identify thematic patterns in texts based on the relation of words within sentences, providing context to their meaning and therefore improving the analysis of their salience. To function, these models tap into libraries of sentence-based transformer models, which are pre-trained on vast amounts of existing texts, allowing them to ‘understand’ contextual references.
This is particularly relevant when it comes to political text analysis. For example, we know ‘right-leaning’ refers to an ideological preference towards socio-economic and cultural policies of the right-wing, rather than someone physically leaning on the right.
What does it have to do with polling?
In polling research, most questions are designed to be ‘closed’ rather than ‘open’ – that is to say, respondents are given a list of specific answer options to choose from. While this allows us to swiftly measure the general public stance on an issue, it does not provide any depth of insight into those views, nor does it pick up public opinions not in the pre-selected list of answer options.
Previously, open text responses have been analysed manually, but this is a vastly time-consuming task, and can create inconsistencies in the interpretation of people’s responses. Topic modelling streamlines the process of identifying themes and classifying responses. Additionally, it makes the process replicable and transparent, where anyone can re-run the model and obtain the same results.
Why use it now?
Artificial intelligence can offer new insights into information that was already available, but has not been analysed systematically, until now. The analytical power it provides to different industries is a popular and heated subject of discussion. We are aware the use of this technology on political surveys is still nascent, and therefore know that it is paramount we develop our model methodically. While we use a unique fine-tuned algorithm to analyse open-response data, there is human supervision at each step of the process. Most importantly, we revise our results meticulously and run internal checks before publishing any findings.
YouGov are continuing to offer innovations and new products in the AI space - reach out to us if you think our AI tracker could be of use to you in your future projects.
See the full results for each survey below
Photo: Getty
