Natural Language Processing (NLP) is the ideal tool to measure the diversity and inclusion of a corporate environment. By using a broad range of techniques, ranging from sentiment analysis to personality classification, we answered the call of a multinational company that needed to check the presence of potential biases in its workforce.

Introduction

Diversity and inclusion (D&I) are crucial components of a successful corporate environment. Diversity refers to the differences in people, including their race, gender, ethnicity, religion, age, sexual orientation, physical ability, and other characteristics. Inclusion, on the other hand, means creating an environment where everyone feels respected, valued, and supported, regardless of their differences.

D&I leads to better decision-making since diverse groups can consider more viewpoints and come up with creative solutions that a homogeneous group may not have considered. Moreover, inclusive companies tend to have higher employee engagement and retention rates. In fact, when employees feel valued and supported, they are more likely to be committed to their work and remain with the company long-term. Finally, companies that prioritize diversity and inclusion tend to have a better reputation with both customers and employees.

Big 5 Framework

The Big Five personality traits is a suggested taxonomy or grouping for personality traits developed from the 1980s onward in psychological trait theory.

• Openness to experience: inventive/curious vs. consistent/cautious
• Conscientiousness: efficient/organized vs. extravagant/careless
• Extraversion: outgoing/energetic vs. solitary/reserved
• Agreeableness: friendly/compassionate vs. critical/rational
• Neuroticism: sensitive/nervous vs. resilient/confident

When factor analysis is applied to personality survey data, it reveals semantic associations, i.e., some words used to describe personality aspects are often applied to the same person. For example, someone described as conscientious is more likely to be described as “always prepared” rather than “messy.” These associations suggest five broad dimensions used in common language to describe the human personality, temperament, and psyche.