A new study by psychologists from Nanyang Technological University, Singapore (NTU Singapore) reveals a correlation between extroverts and their word choices. The finding suggests that online personality prediction tools need better linguistic indicators to improve digital marketing strategies. Marketing companies have already begun working on these tools.
In our modern world, these companies utilize predictive algorithms to forecast what customers want according to online behaviors. Digital marketing services similar to digital marketing company in Brisbane also take advantage of online data and machine learning to better understand the psychology behind consumers’ choices. Of course, this research can provide insight into ways to improve targeted advertising.
For instance, extroverts may respond better to marketing, which corresponds with their personality. Retailers could then appeal to these consumers with more extroverted, creative language. However, online personality prediction tools utilized by marketing firms today need some improvement. They lack accuracy because they only apply in certain situations and applications.
Lead investigator of the study, Associate Professor Lin Qiu from the Psychology program at the NTU School of Social Sciences, said,
“Current machine learning algorithms for personality prediction can seem like a black box — there are many linguistic indicators that can be included in their design, but many of them are dependent on the type of computer application used. This may lead to biases and overfitting, an error affecting the performance of the machine learning algorithms. This begs the question — how should we create robust and accurate personality predictions?”
The research discovered a link between extroverts and their tendency to choose specific types of words. The study revealed that extroverts tended to use more positive language and “social process words.”
How psychologists discovered the correlation between extroverts and word choice
Using text analysis tools, psychologists define positive emotion words as those portraying an enjoyable emotional state. Words that describe positivity include ‘love,’ ‘happy,’ ‘blessed,’ ‘beautiful’ or ‘nice.’ Social process words describe those which contain personal pronouns except for ‘I.’ These words also show social intentions or goals, such as ‘meet,’ ‘share,’ and ‘talk.’
“This is the first time a relationship has been established between extroverts and their tendency to use the two categories of words. As it is a small correlation, we believe that stronger linguistic indicators are needed to improve machine learning approaches, amid rising interest in such tools in consumer marketing,” Assoc Prof Qiu said.
The research was published in the Journal of Research in Personality in December 2020. The NTU team said that these findings could help marketers develop better linguistic predictors for machine learning algorithms. This will, in turn, enhance software tools for personality prediction.
How the team carried out the study
Prior studies reviewed by the NTU psychologists have found a link between extroversion and specific word choices. Extroverts tend to have more positive emotions and enjoy socializing more than introverts. The team positively associated this personality trait with increased usage of “positive emotion” and “social process” words. However, the strength of this correlation varies across the studies exploring extroversion and language.
To prove the strength of these linguistic predictors, the team reviewed 37 studies on the topic. They categorized extroversion using internationally recognized personality type questionnaires. In the future, the NTU team wants to study the relationship between extroverts and other word choices.
Currently, machine learning and predictive tools can help companies and marketers in business endeavors. However, the NTU psychologists say that the design of these models could use improvement. They hope their research will help marketers better understand how certain words can appeal to different personality types. Furthermore, they expect the study will bring about improvements in machine learning tools used for personalty prediction.
These same tools can likely help predict words that introverts use as well. Of course, most people fall somewhere on the spectrum between introverts and extroverts. Personality can change depending on many factors, and therefore, can’t be reduced to just word choices. However, there are certain traits that introverts and extroverts exhibit, which give their underlying personality away.