Value-based prediction of election results using natural language processing: A case of the New Zealand General Election

In this article, we report the results of a study that tested a values-based method of predicting political election results.

Background

Election polling is a standard practice in most democracies (Lewis-Beck, 2005). Substantial advancement in the methodology has been made since the 1948 US Presidential Election, in which President Harry Truman retained his office after all pre-election forecasts pronounced his defeat (Rosenberg, 2015). Pollsters' poor management of sample frame deficiencies was blamed for the infamous headline in the Tribune, "Dewey defeats Truman" that went to press before the election results were announced (Jones, 2007).

Most pollsters and the general public refer to the estimates of pre-election polls as forecasts. A close examination of the methodology reveals that they are the...

Not a subscriber?

Schedule your live demo with our team today

WARC helps you to plan, create and deliver more effective marketing

  • Prove your case and back-up your idea

  • Get expert guidance on strategic challenges

  • Tackle current and emerging marketing themes

We’re long-term subscribers to WARC and it’s a tool we use extensively. We use it to source case studies and best practice for the purposes of internal training, as well as for putting persuasive cases to clients. In compiling a recent case for long-term, sustained investment in brand, we were able to support key marketing principles with numerous case studies sourced from WARC. It helped bring what could have been a relatively dry deck to life with recognisable brand successes from across a broad number of categories. It’s incredibly efficient to have such a wealth of insight in one place.

Insights Team
Bray Leino

You’re in good company

We work with 80% of Forbes' most valuable brands* and 80% of the world's top top-of-the-class agencies.

* Top 10 brands