‘Happiness Index’ for SA, using Big Data, to measure real-time economic sentiment

Professor Talita Greyling, a researcher in the field of wellbeing economics and development economics at the University of Johannesburg (UJ) along with Auckland University of Technology’s Dr Stephanie Rossouw have developed a ‘happiness index’ that measures the emotional temperature of the economy and track the country’s happiness sentiment.

Says Prof Greyling: “Traditionally, economists measured the wellbeing of people or a nation by using objective economic indicators such as gross domestic product (GDP). These indicators do not measure wellbeing, but merely specific conditions, which is believed to lead to a good life.”

According to Prof Greyling, when people are happy and satisfied with their life, it could signal that they have a higher level of wellbeing. “Wellbeing measures capture valuable information, which is not provided, in other indicators, such as real GDP per person.”

Gross National Happiness (GNH) refers to the level of happiness for a group of citizens or nations and the best-known measures to date are the Gallup World Happiness Index (WHI), World Value Survey and the Happy Planet Index.

According to the WHI, South Africa ranked 106th out of a possible 156 countries for the year 2019, with a score of 4.7. The happiness is measured on a scale from zero to 10. With zero being very unhappy, five (5) neutral and 10 very happy. Governments are able to influence GNH through the institutional and policy framework they establish. The links between the government and GNH can operate in both directions: what governments do affects GNH, and in turn, the GNH of citizens in most countries determines what kind of governments they support. These type of happiness indicators measures happiness on an evaluative level, thus related to a question such as “how satisfied are you with your life in general”, thus, it has a longer-term view and based on survey data. This is not always what is needed in an economy often we rather need a measure of affect happiness – therefore measuring the emotion of the moment is key it is this type of happiness that influences the decision-making process of people.

The question becomes, how do you go about achieving this? One obvious answer is to simply ask everyone in a country, every day, whether they are happy.

As this is an impossible task, Prof Greyling (UJ) and Dr Rossouw (Auckland University of Technology), propose an alternative solution. They construct a GNH index, and do this by following what people say, every day, about life, using social media and the voluntary information sharing structure of Twitter, they determine the affect happiness of South Africa’s citizens. They use sentiment analysis by applying sophisticated software to Tweets. Sentiment analysis is the procedure of text analysis that labels a Tweet as either having a positive, neutral or negative sentiment, which they then apply to a sentiment balance algorithm, to derive a happiness score.

The scale of the happiness scores is between one (1) and 10, with five (5) being neutral, thus neither happy nor unhappy. In this manner, we are able to see the change in the ‘mood’ of a nation given economic, political or social events, as early as one hour after it happened.

Prof Greyling pointed out that the use of big data to analyse the wellbeing of people, such as what we are currently doing, is the future, especially because of the vast number of observations and the benefit of measuring the “mood” at almost real-time.

This index was launched in South Africa on 30 April 2019, the week before the national election and since then it has been launched in New Zealand (14 May 2019) and Australia (16 May 2019) to monitor the sentiments around the elections in the respective countries, she further commented.

South Africa currently has over 8.3 million active Twitter users (approximately 15% of the population), which provides us with much larger sample size, than can be found in any other survey (apart from the national Census). To put this in perspective, Gallup World Poll Data, which is used to determine the World Happiness Index, surveys on average 1000 people in South Africa once a year to calculate the WHI scores.

Prof Greyling added that what they have learned so far from collecting data during the elections in South Africa is that it closely tracks the political energy in the country and furthermore GNH is correlated to economic indicators. “When considering the All Share Index of the Johannesburg Stock Exchange (JSE), we saw that if the happiness level changes, the All Share Index moves in the same direction. With further testing we found the relationship getting stronger with a time difference of three hours, thus if three hours after a change in the level of happiness we observed a 50% correlation and the relationship is significant at a level of 99%, thus we can say that we are 99% sure that we can trust this result. This indicates that our GNH index is likely a leading indicator if we consider the financial markets. That is, the data gathered gives an indication of what may happen in the future.

South Africans’ Happiness levels from 30 April to 12 May 2019

“Economic indicators are measured on a daily basis and we constantly debate the impact of policy on these. Yet, we neglect to grasp the most important part. Changes in economic indicators are based on the decisions South Africans make……policy is simply the rules of the game….but it is South Africans playing the game.”

Prof Greyling poses the question: Why would we neglect to measure affect happiness every day when this reveals the emotions and feelings of the people, thus the real measure of their wellbeing? “We all know that the assumption of human beings, being rational and therefore making rational decisions, is not entirely accurate. We are emotive human beings and our emotions govern our decisions. If governments insist on ignoring the happiness of their people, they do so at their own economic peril.

We have launched this index with the goal of measuring affect happiness on a daily basis, alongside other economic indicators, because we can see the importance of complementing ‘hard’ objective indicators with ‘soft’ subjective indicators. In South Africa, we were able to see how the collective happiness changed, first from being happy and positive about “election day” and then decreased the day thereafter with the political energy deepening and hot debates on the election results.

As can be seen from the GNH graph, the emotions of South Africans were on a roller coaster from pre-elections to post elections, with election day reaching a higher level of happiness of 6.48, but was surpassed by “Mother’s day” which reflected a very positive sentiment among South Africans.

Professor Talita Greyling
Professor Talita Greyling
Share this

Latest News

All News