Companies use NLP-based sentiment analysis to generate intelligence  

The complications caused by the pandemic are forcing companies across sectors to use artificial intelligence (AI)-based sentiment analysis.

For example, after the Reserve Bank of India (RBI) lifted the moratorium on loan repayments, banks and non-banking finance companies (NBFCs) had to deal with a backlog of loans. To speed up the process, many NBFCs and banks have started adopting Natural Language Processing (NLP) based solutions to gauge the borrower’s mood from their conversations.

An example is Credgenics’ sentiment analysis tool, which uses speech recognition and chat analysis via automated voice bots and WhatsApp bots to generate information about borrowers. These have enabled NBFCs and banks to identify problems faced by borrowers in repaying loans. Credgenics claims that more than 60 lending institutions including ICICI Bank, Axis Bank and IDFC First Bank use its software-as-a-service (SaaS) platform based on sentiment analysis.

“This allowed them to plan the communication strategy and channel for lenders for optimal results,” said Anand Agrawal, co-founder and chief technology officer of Credgenics. He said that sentiment analysis helps to extract subjective meaning from the text and determine the sentiment of the borrower. It is an ideal tool for reviewing unstructured content about a particular borrower’s digital communications for insights.

According to Agrawal, sentiment analysis has enabled credit institutions to improve debt collection rates by 15-20% and recover 70-95% of bad debts.

Sentiment analysis also helps companies stem churn. Businesses use these tools to identify employees who might leave and retain them with benefits, pay raises, and a better work environment. “We’ve seen customers retain 85% of their top talent (using sentiment analysis),” said Tanmaya Jain, founder and CEO of inFeedo, a SaaS company that provides sentiment analysis tools to more than 200 companies, including Samsung, Airtel, Xiaomi and Lenovo in India.

Jain said one customer in India, a large unnamed business with more than 3,000 employees, is struggling to retain employees after a major merger with another company. After deploying a sentiment analysis chatbot, the company was in a better position to gauge employee sentiment and was able to increase retention by over 10%.

InFeedo AI chatbot offers information based on interaction with employees. The bot uses NLP to understand context and identify employees who seem disengaged and more likely to leave.

The use of sentiment analysis is not entirely new. Previously, the use of NLP for sentiment analysis was limited to tech giants like Google and Amazon, who had more data and AI and ML engineers to experiment with.

Among Indian companies, e-commerce firms like Flipkart were the first to adopt it to understand customer sentiment by analyzing user reviews using NLP.

NLP, a subset of artificial intelligence, enables certain software to read, understand, and infer context in text and spoken words just like humans. It can be used in any area where human conversation is involved. Before NLP, most AI-based chatbots operated and responded within a fixed set of questions and answers.

Sentiment analysis has been around for years, but interest in it is growing among many businesses now that the underlying NLP technology has become much more mature. “What has changed is that now NLP and sentiment analysis are becoming much more mature in terms of accuracy and readiness,” said Jayanth Kolla, co-founder of market research Convergence Catalyst.

He added that the talent pool of people working on it has increased in the recent past, which in turn has led to greater adoption.

According to Kolla, the demand for sentiment analysis has increased since the pandemic. He noted that many HR technology firms use sentiment analysis to read chats on platforms like LinkedIn and Glassdoor to rate companies.

Demand for inFeedo has tripled since the pandemic. “Earlier, when employees were on premises, it was easier to understand the sentiments of employees, but with hybrid and remote work and video conferencing fatigue, it is difficult for leaders to gauge the sentiment of their employees,” said Jain.