“The most important decision you take is to be in a good mood.” – Voltaire

Where We Started

People’s moods differ throughout time. Sometimes, we are affected by personal matters, social affairs, or the weather. Other times, more prominent aspects might affect our mood; we can be affected by the outcome of political elections, international disputes, or long-lasting pandemics. However, we constantly talk about our mood and its causes.

Our Motivation

Provided with the QuoteBank data set, we grew interested in what it could reveal about the truth in the everyday talk about our mood. For example, does the temper become better towards the weekend, or do we all love Mondays deep inside? Is the mood better during the sunny summer and worse when the cold hits us in the winter? Moreover, what can we say about the trends of the mood in the media throughout time?

Why Is It Important?

Based on our initial questions, our thoughts wandered into what we could say specifically about the mood in the media. As the media sets the agenda for the public debate, it is intriguing to see how much positivity and negativity reach the readers’ minds. Which media outlets provide us with the most positivity, and which are more gloomy? Moreover, can we see any differences across the subsets of speakers in the data set? For example, are politicians’ quotes more pessimistic than others? Do women tend to be more optimistic than their peers?

We aim to present our findings on the abovementioned topics in the upcoming data story. Starting with the QuoteBank data set provided by dlab @ EPFL, we will utilize information from Wikidata to research our questions by sentiment analyses.

Key Insights

  • There is no evidence for significant variations in the mood in media quotations across weekdays or months
  • The mood in the media became significantly more negative in the first phase of the COVID-19 pandemic
  • There are statistically significant differences in mood and subjectivity across media outlets. For example, sports and celebrity magazines tend to be more positive and subjective than daily newspapers
  • There are no significant differences in mood in quotes from men and women
  • On average, quotations from politicians are more negative than the average quotation

Our Data and Methods

Photo credit: Unsplash

Initially, we want to give a feel about the data and provide some initial analyses and comments on the methods we will use in our work.

Quotebank

The Quotebank data set provides quotations in the media from more than a decade. In total, 178 million quotations from 2008 to 2020 are attributed with probable speakers and dates. Using machine learning methods, dlab @ EPFL has built a framework for recognizing and attributing quotations from media articles, thus building the data set. However, we have only utilized quotations from 2015 to 2020, distributed through the years as in the following diagram: