January 19th, 2021
Using AI to unearth the unconscious bias in job descriptionsRSS Share Category: Wave
By: Parul Pandey and Shivam Bansal
“Diversity is the collective strength of any successful organization
Unconscious Bias in Job Descriptions
Unconscious bias affects us all, in one way or the other. It is defined as the prejudice or unsupported judgments in favor of or against one thing, person, or group as compared to another, in a way that is usually considered unfair. Unconscious bias is being discussed in colleges, universities, and across big and small workplaces today. One of the most prominent examples of unconscious bias is observed in the hiring process adopted by companies. Often, the job bulletins that are put forth contain elements that favor a particular gender or group. Biased job descriptions not only limits the candidate pool but also diversity in the workplace. Therefore, the companies need to check out for any biases in the job descriptions and eliminate them to create a healthy and fair culture in an organization. So how can one detect biased job descriptions in the first place? Well, Artificial Intelligence technologies can come to the rescue.
How can Artificial Intelligence provide an answer?
Today machine learning and Artificial Intelligence have made it possible to analyze data from various sources with a lot more accuracy and precision. Whether it is structured or unstructured data, AI-backed technologies can provide superior results compared to manual processing. Hence, It’ll be a great idea if these AI applications are infused into a platform that enables business users to directly interact with data without a lot of hassle and complexities. Well, H2O Wave has been created to do precisely this, and in this article, we’ll clearly see how to implement this idea. But before we go further, let’s quickly understand what H2O Wave is and what are its advantages.
H2O Wave is an open-source Python development framework that makes it fast and easy for data scientists, machine learning engineers, and software developers to develop real-time interactive AI apps with sophisticated visualizations. H2O Wave accelerates development with a wide variety of user-interface components and charts, including dashboard templates, dialogs, themes, widgets, and many more. There are thousands of potential use cases, and some of them are:
Using Wave’s ‘Hiring Bias’ App to detect unconscious bias in the Job Description dataset.
Let’s now see how AI can help us detect unconscious bias in a dataset containing job descriptions. In this article, we shall be working with a preprocessed version of the Los Angeles Job Description dataset from Kaggle, which includes the following attributes:
Our job is to detect whether the text in the
description_text the column contains unconscious bias or not.
This dataset is first loaded into the app. The ‘Hiring App’ consists of several machine learning algorithms and models that analyze different parts of the job description text and perform analysis based on the word choices, text structure, tone, sentiment, etc. The app then generates a detailed report containing multiple insights and findings in form of a dashboard. Here are some of the detailed findings grouped under the following headings, i.e., Word Choice, Text Structure, or Tone / Sentiment.
1. Analysis of Word Choice
Unconscious Bias in job descriptions towards a specific gender can limit the candidate pool and diversity. The figure below shows some of how the choice of words can lead to bias.
Let’s see some of the insights presented by the app :
- Use of Gendered Keywords in Job Descriptions
Using gender-specific words in the job description can isolate a specific gender from applying to certain jobs. It has been observed that words that are more “aggressive,” “assertive,” or “independent” typically put off women from applying to specific roles. The plots below show the male and female-specific keywords identified in the dataset.
- Higher use of Superlatives
The following example shows certain job descriptions where highly superlative keywords, specifically “Master” and “Expert,” are used. These keywords have a very strong masculine tone and hence show a preference towards a particular gender.
- Use of Gendered pronouns
It is a wrong practice to specify only two genders in the job descriptions in the form of “he/she.” This usage is another form of unconscious gender bias that is commonly present in the descriptions today.
2. Analysis of Text Structures
“A well-written, complete, and insightful job description can result in attracting some of the top and diverse talents for the role.” On the other hand, a description that lacks vital features (for example — an optimal word limit, choice of the words, language used, overall tone) may result in attracting fewer candidates.
The text structure of a job description can be analyzed in several ways, namely :
- Analysis of Difficulty level of keywords in job descriptions
Since readability is of paramount importance, it is a good idea to focus on the words that are difficult to read for people and to eliminate them. The graph below shows the high usage of difficult words in the descriptions of various jobs.
- Analysis of the readability of Job descriptions
Similarly, companies should refrain from making job descriptions too complex or challenging to read. For instance, on analysis, it was found that the following job descriptions for the following posts were the least readable.
3. Analysis of Tone / Sentiment
Sentiment analysis is a sub-field of Natural Language Processing (NLP)that tries to identify and extract opinions from a given text. Sentiment analysis of the job descriptions can help the companies to gauge their tone and overall sentiment. The sentiments or the tone conveyed in the job descriptions should not be too negative or demanding, resulting in fewer people applying for the job.
- Overall Sentiment of Job Descriptions
Use of sentences and words that convey moderate or high negative sentiments should be avoided. The following plot shows the distribution of the negative sentiments in the job descriptions.
- The tone of Job Descriptions
Companies must ensure that the tone of the job descriptions shouldn’t be too negative. For instance, keywords containing negative sentiments that have been automatically highlighted below should be avoided.
- Use of Strict Keywords in Job Descriptions
Again, excessive use of demanding keywords in nature is also not desirable in a job description. Phrases such as “who fail,” “will not be considered,” “must-have,” etc., should be avoided or replaced with positive and encouraging words like “good to have,” “add-on,” etc.
The analysis clearly demonstrated that the idea of job descriptions is to encourage a wider group of people to apply. Thus, the choice of language and words in job descriptions plays a crucial role in promoting applicant diversity. Hence, factors like content, tone, language, and format can directly or indirectly influence the hiring process of a company.
Create your own apps with H2O Wave