How The Gender of Language Measures ESG Behaviour
Indexica creates measurement factor based on male versus female language
Indexica, a leader in the NLP alternative data space, announced the release of a new NLP factor to be used in socially responsible investing decisions. Gender is a linguistically constructed metric that is built upon the structural roots of sentiment analysis. Rather than classifying words, phrases, and events as positive or negative, Gender classifies words, phrases, and events as either more aligned with female or male dominant linguistic patterns. Linguistically speaking, male-dominant language often includes macho talk. Female-dominant language is often softer, more caring, and conscientious. The metric was built by analyzing millions of quotes from men and women, and then classifying words as either “male” or “female” leaning, based on their volume of usage by gender.
The metric is applied to the discourse around public companies in news articles. Across large textual corpus samples, female-dominant language lines up well with the types of events and behaviours that lead companies to receive high ESG scores from the leading researchers on the topic, who are often indexers. Male dominant language on the other hand often correlates with low ESG scores. Indexica releases the metric daily based on streaming news, and thus, the Gender metric is a simple and fast way to obtain real-time values and to monitor ESG trends across portfolios non-subjectively.
Investing in companies measured as responsible based on criteria including environmental, social, and governance factors is gaining traction. While the research on whether ESG investing results in outperformance is inconclusive, the hope is that in the future, not only will company behaviour improve if investors allocate capital based on these metrics, but investor returns will follow.
Zak Selbert, CEO at Indexica commented, “It’s still the wild west when it comes to ESG metrics and investing. The subjective categories considered important and the inconsistent human analysis that goes into scoring, is problematic and ever-evolving. Animal agriculture, for example, is barely a part of most ESG scores yet is one of the most important factors impacting our environment, health, and principles. Over time, ESG models will have to move towards measuring this.”
Indexica’s Gender metric correlates with traditional ESG scores from the major providers especially at both ends of the spectrum, yet does so in a non-subjective and real-time manner. Measuring the tonality of conversation using this metric would have yielded consistent and real-time scores whether measuring company behavior in the imperialistic era, the industrial revolution, or the current era of yearly revolutions since the score isn’t creating subjective moral categories. Current ESG scoring mechanisms cannot do this because ethical values are ever-changing, whereas gender tonality has always correlated well with “good” and “bad” ESG behaviours.
Indexica’s mission is to agnostically identify and measure what drives markets. Indexica’s Futurity metric, for example, has systematic predictive power across investable assets. But it is also Indexica’s job to create metrics that will measure what will drive markets going forward. And because the yardstick for measuring ESG behaviour will evolve, using language tonality rather than human subjectivity is likely to result in more accurate scoring, consistency, and faster actionable data. While at the moment, Gender scores have predictive value only on a case by case basis, over time, the expectation is that Gender will have systematic predictive value.
Indexica measures what’s happening in the world by quantifying events, trends, and opinions in news documents using natural language processing. Using machine learning, Indexica looks for signals in the measurements to see whether there are leading indicators that foreshadow market movements.
Contact: Zak Selbert