One need look no further than the latest uproar in politics, or the quick spread of a brand’s ill-advised move to know the flash-flood speed of social media’s swell. Twitter is the modern Town Crier, multiplied, amplified and accelerated by the power of the Internet. But how influential is it to a company’s reputation?
US-based iSentium has proven that the crowd makes a measurable impact on stock prices – the ultimate measure of a brand’s value. While social sentiment is among many factors that affect asset value, its role increases as the shouting on Twitter grows increasingly central to public discourse. Take for instance when e.coli was discovered at Chipotle. What would have once been isolated to a local news story became the outrage of a crowd, and the company took a serious hit.
In this climate, companies with access to accurate, real-time sentiment data can use this insight to grow profits, to protect brand and to stay aware.
The problem may be clear, but the solution is challenging Both Brexit and the American presidential election prove the fallibility of traditional methods and the need to understand the voice of the crowd. But finding meaning in a tidal wave of human expression is hugely difficult. While many tech companies are throwing incredible resource at measuring volume and sentiment in social media, they rely on the binary predictability of computer language, versus being able to capture the actual voice of the people.
This poses two enormous challenges – first the operating expense of processing such a huge volume of data. Think of the $3b AWS cost filed by Snap and you get a sense. iSentium’s cracked that with extreme speed computing that processes the Twitter firehose on the equivalent of a lap top.
The other is that this ‘data’ is in fact language – human expression in its most casual. iSentium’s engine is driven by a team of Noam Chomsky-trained linguists to handle the complexity and creativity of real human language, as we talk, Tweet, text. For example, the number of times a word is mentioned is irrelevant without context. Also, the way we refer to a brand varies dramatically from person-to-person, especially in short format. People don’t communicate with the goal of being measured by AI. Think of Coke, Coca-cola, or its stock ticker KO.
Platforms like Twitter, Facebook, and Slack force brevity, which obscures the grammar and other structural cues binary natural language processing (NLP) relies on to make sense of words – so each of the more than 3 billion Tweets each month is in a personal shorthand, and iSentium has done a decade of work to figure out how to find the meaning in each – at the incredible speed and volume they’re being pushed.
Too risky to ignore, and equally rewarding to get right Perhaps this social outcry is a flash in the pan to be ignored? More accurately, ignore the sentiment of the crowds and see your brand’s value irrevocably damaged.
Think about it. This personal expression is where people’s intentions are most clear. The olden days of surveys and polling are no longer sufficient. While iSentium doesn’t replace traditional market research, it shows that real-time understanding of the wisdom of the crowd is essential for smart traders, brand managers and other businesses who rely on understanding market dynamics.
And it works. Well. The proof is in the numbers.
The unique, immediate data stream delivers edge directly to financial institutions that have struggled to find it in recent years — in a way that arrives well before other intelligence, is actionable and is immediately measured in money made. For example, a dedicated JPM/iSentium index (Bloomberg:JPUSISEN), applying iSentium’s daily intelligence on the underlying assets of SPY generated cumulative returns of 67.23% vs. 23.33% using the traditional buy and hold approach.
Link to original publication can be found here: http://partners.wsj.com/the-business-debate/tomorrows-business-today/business/win-wisdom-crowd/