We are often asked by talent leaders and hiring managers whether interviews conducted via a text-based chat disadvantage people who have English as a Second Language (EASL).
While that may seem intuitive, the data tells a different story.
Aggregate results across a variety of Sapia.ai clients that use our AI Smart Interviewer indicate that EASL candidates, in general, perform better than Native English speakers.
While these results may seem surprising, the science that underpins our AI Smart Interviewer has been created to mitigate bias, and we test this constantly.
Standard testing includes the “4/5th rule”, the industry standard test for adverse impact. It ensures the selection ratio of a minority group is at least four-fifths (80%) of the selection ratio of the majority group.
When comparing Native English Speakers with Non-Native English Speakers (EASL), it is shown that EASL candidates are scored higher on average by our AI Smart Interviewer and therefore auto-progressed at a higher rate than those whose native language is English, achieving a 4/5ths rule score of 100%.
Assessing language using Sapia.ai
When it comes to assessing language skills using Sapia.ai proprietary written language assessments, we have developed two aggregate measures called “basic communication skills” and “advanced communication skills”.
– Basic skills look for language fundamentals like spelling, grammar, readability etc.
– Advanced skills look at the sophistication of language (e.g. vocabulary).
It is important to note that the dimensions used within each measure such as spelling and grammar are weighted in such a way that not all misspelled words or grammatically incorrect sentences result in a penalty. These aggregate measures are benchmarked and validated using our large interview dataset across multiple role families.
Further, in Sapia.ai assessments, these measures are not always weighted the same and are set depending on how important language skills are for a particular job.
For example, for a customer-facing retail role, “basic skills” might be set as “medium” and “advanced skills” as “low” or as simply ignored. A retail team member may be required to jot down notes or write the occasional report or email. Basic writing skills may be helpful but not essential, hence the “medium” weighting and minimal impact on their overall score. Other personality traits and behavioral competencies may play a stronger role in determining role-fit.
Secondly, the scores are benchmarked within a relevant population. A retail worker’s “basic skills” score is not compared against graduates or call center staff.
Here’s how the scoring might work:
Maria applies for a retail role and gets a basic skills score that puts her in the top 20% of the population, that is, within a population of retail candidates. This percentile is used in the final score calculation. That way no one is disadvantaged, and candidates are only compared within a comparable group. The basic skills score received by Maria that placed her in the top 20% of retail applicants is 54/100.
In comparison, Michael, a graduate applicant, receives a basic skills score of 72 and is in the top 30% of graduate applicants. Michael has scored higher than Maria in his basic skills, but in their respective populations, Maria has done better than Michael.
There are also other factors to consider when thinking about smart chat interviews and their impact on EASL candidates.
In a spoken test or video test, candidates have fewer chances to re-record their answers. In our Chat Interview™, we give candidates unlimited chances to refine their answers, allowing them to edit the text until they are ready to submit. An EASL candidate will have as much opportunity as they want to refine their answers with no pressure.
Candidates can do the test at their own pace, so the time taken to complete the test is not a factor that will impact the scores. An EASL candidate will have enough time to work on the language and get it right.
You may still be wondering how we ensure EASL candidates’ personality traits and behavioral competencies are also accurately assessed.
Our Chat Interview™ uses Natural Language Processing, machine learning, and optimization methods to score structured interview responses, fairly and consistently.
Our scoring leverages data from over 1 billion words written by over 3.5 million diverse candidates across many different role families and regions.
Based on one’s use of language, we derive signals that matter, like personality and behavioral competencies, that are then used in a predictive algorithm based on the ideal candidate profile to generate a score and recommendation.
We don’t use simple keyword matching, and we consider more than just the words used. Phrasing, syntax, structure, and context all matter. Perfect grammar and spelling don’t matter for the majority of constructs.
Taken together, our highly tuned assessment models combined with the validity of structured interviews represent a far more enjoyable and reliable assessment experience for EASL candidates, especially when compared to traditional assessments.
Being data-driven means we can constantly and vigilantly check that EASL candidates are not disadvantaged in how they are assessed.
Related
Blog
The AGC Debate: Are AI-Written Interview Answers a Red Flag or Smart Strategy?
Every day, we read stories of increased fake or AI-assisted applications. Tools like LazyApply are just one of many flooding the market, driving up applicant volumes to never-before-seen levels.
As an overwhelmed hiring function, how do you find the needle in the haystack without using an army of recruiters to filter through the maze?
At Sapia.ai, we help global enterprises do just that. Many of the world’s most trusted brands, such as Qantas Group, have relied on our hiring platform as a co-pilot for better hiring since 2020.
Our Chat Interview has given millions of candidates a voice they wouldn’t have had – enabling them to share in their own words why they’re the best fit for the role. To find the people who belong with their brands, our customers must trust that their candidates represent themselves. Thus, they want to trust that our AI is analysing real human answers—not answers from a machine.
The Rise of GPT
When ChatGPT went viral in November 2022, we immediately adopted a defensive strategy. We had long been flagging plagiarised candidate responses, but then, we needed to act fast to flag responses using artificially generated content (‘AGC’).
Many companies were in the same position, but Sapia.ai was the only company with a large proprietary data set of interview answers that pre-dated GPT and similar tools: 2.5 billion words written by real humans.
That data enabled us to build a world-first:- an LLM-based AGC detector for text-based interviews, recently upgraded to v2.0 with 99% accuracy and a false positive rate of 1%. An NLP classification model built on Sapia.ai proprietary data that operates across all Sapia.ai chat interviews.
Full Transparency with Candidates
Because we value candidate trust as much as customer trust, we wanted to be transparent with candidates about our ability to detect artificially generated content (AGC). As an LLM, we could identify AGC in real time and warn candidates that we had detected it.
This has had a powerful impact on candidate behaviour. Since our AGC detector went live, we have seen that the real-time flagging acts as a real-time disincentive to use tools like ChatGPT to generate interview responses.
The detector generates a warning if 3 or more answers are flagged as having artificially generated content. The Sapia.ai Chat Interview uses 5 open-ended interview questions for volume hiring roles, such as retail, contact centre, and customer service, and 6 questions for professional roles, such as engineers, data scientists, graduates, etc.
Let’s Take a Closer Look at the Data…
We see that using our AGC detector LLM to communicate live with candidates in the interview flow when artificial content has been detected has a positive effect on deterring candidates from using AI tools to generate their answers.
The rate of AGC use declines from 1 question flagged to 5 questions – raising the flag on one question is generally enough to deter candidates from trying again.
The graph below shows the number of candidates, from a total of almost 2.7m, that used artificially generated content in their answers.
Differences in AGC Usage Rate by Groups
We see no meaningful differences in candidate behaviour based on the job they are applying for or based on geography.
However, we have found differences by gender and ethnicity – for example, men use artificially generated content more than women. The graph below shows the overall completion ratios by gender – for all interviews on the left and for interviews where the number of questions with AGC detected is 5 or more on the right.
Perception of Artificially Generated Content by Hirers.
We’re curious to understand how hirers perceive the use of these tools to assist candidates in a written interview. The creation of the detector was based on the majority of Sapia.ai customers wanting transparency & explainability around the use of these tools by candidates, often because they want to ensure that candidates are using their own words to complete their interviews and they want to avoid wasting time progressing candidates who are not as capable as their chat interview suggests.
However, some of our customers feel that it’s a positive reflection of the candidate, showing that they are using the tools available to them to put their best foot forward.
It’s a mix of perspectives.
Our detector labels it as the use of artificially generated content. It’s up to our customers how they use that information in their decision-making processes.
This concept of having a human in the loop is one of the key dimensions of ethical AI, and we ensure that it is used in every AI-related hiring product we build.
Interested in the science behind it all? Download our published research on developing the AGC detector 👇
Research Paper Download: AI Generated Content in Online Text-based Structured Interviews
Blog
Joe & the Juice Partners with Sapia.ai, Scaling an Exceptional Candidate Experience and Cutting Time to Hire
Read the full press release about the partnership here.
Joe & the Juice, the trailblazing global juice bar and coffee concept, is renowned for its vibrant culture and commitment to cultivating talent. With humble roots from one store in Copenhagen, now with a presence in 17 markets, Joe & The Juice has built a culture that fosters growth and celebrates individuality.
But, as their footprint expands, so does the challenge of finding and hiring the right talent to embody their unique culture. With over 300,000 applications annually, the traditional hiring process using CVs was falling short – leaving candidates waiting and creating inefficiencies for the recruitment team. To address this, Joe & The Juice turned to Sapia.ai, a pioneer in ethical AI hiring solutions.
A Fresh Approach to Hiring
Through this partnership, Joe & The Juice has transformed its hiring process into an inclusive, efficient, and brand-aligned experience. Instead of faceless CVs, candidates now engage in an innovative chat-based interview that reflects the brand’s energy and ethos. Available in multiple languages, the AI-driven interview screens for alignment with the “Juicer DNA” and the brand’s core values, ensuring that every candidate feels seen and valued.
Candidates receive an engaging and fair interview experience as well as personality insights and coaching tips as part of their journey. In fact, 93% of candidates have found these insights useful, helping to deliver a world-class experience to candidates who are also potential guests of the brand.
“Every candidate interaction reflects our brand,” Sebastian Jeppesen, Global Head of Recruitment, shared. “Sapia.ai makes our recruitment process fair, enriching, and culture-driven.”
Results That Matter
For Joe & The Juice, the collaboration has yielded impressive results:
-
33% Reduction in Screening Time: Pre-vetted shortlists from Sapia.ai’s platform ensure that recruiters can focus on top candidates, getting them behind the bar faster.
-
Improved Candidate Satisfaction: With a 9/10 satisfaction score from over 55,000 interviews, candidates appreciate the fairness and transparency of the process.
-
Bias-Free Hiring: By eliminating CVs and integrating blind AI that prioritizes fairness, Joe & The Juice ensures their hiring reflects the diverse communities they serve.
Frederik Rosenstand, Group Director of People & Development at Joe & The Juice, highlighted the transformative impact: “Our juicers are our future leaders, so using ethical AI to find the people who belong at Joe is critical to our long-term success. And now we do that with a fair, unbiased experience that aligns directly with our brand.”
Trailblazing for the hospitality industry
In an industry so wholly centred on people, Joe & the Juice is paving the way for similar brands to adopt technology that enables inclusive, human-first experiences that can reflect a brand’s core values.
If you’re curious about how Sapia.ai can transform your hiring process, check out our full case study on Joe & The Juice here.
Blog
Sapia.ai Wrapped 2024
It’s been a year of Big Moves at Sapia.ai. From welcoming groundbreaking brands to achieving incredible milestones in our product innovation and scale, we’re pushing the boundaries of what’s possible in hiring.
And we’re just getting started 🚀
Take a look at the highlights of 2024
All-in-one hiring platform
This year, with the addition of Live Interview, we’re proud to say our platform now covers screening, assessing and scheduling.
It’s an all-in-one volume hiring platform that enables our customers to deliver a world-leading experience from application through to offer.
Supercharging hiring efficiency
Every 15 seconds, a candidate is interviewed with Sapia.ai.
This year, we’ve saved hiring managers and recruiters hours of precious time that can now be used for higher-value tasks.
Giving candidates the best experience
Our platform allows candidates to be their best selves, so our customers can find the people that truly belong with them. They’re proud to use a technology that’s changing hiring, for good.
Leading the way in AI for hiring
We’ve continued to push the boundaries in leveraging ethical AI for hiring, with new products on the way for Coaching, Internal Mobility & Interview Builders.