Register for free to
view the full innovation profile.
We are a linguistics-led AI company training computers to *genuinely understand* unstructured text, at scale, leveraging qualitative data to make evidence-based decisions.
About
Wordnerds is a text analytics platform that helps organisations leverage the masses of words written both to, and about themselves and their competitors. Many tools currently on the market provide obsolete word clouds or CX scores, but we believe they are not solving the biggest challenge - language. Language is complex, nuanced, sarcastic, misspelled and in most cases each word can have more than one meaning. Context dictates meaning. Always. We can’t rely on the presence of keywords to determine meaning. Wordnerds have tackled this problem of language by bringing together two key practices: Natural Language Processing (NLP) and Corpus Linguistics. By combining these two areas, we’ve been able to teach computers to understand humans to an accuracy not met by the leading off-the-shelf solutions. In late 2019, against tests of human-marked data, our sentiment analysis of sentence fragments was 31% more accurate than Google NLP, 48% better than IBM Watson. Our SaaS platform allows teams to gather the millions of social media comments, live chat messages, survey responses, complaint emails, forum posts and more, to gather an objective understanding of the data: - Topic Clustering: Our system will pull out what people are talking about and in what numbers - Sentiment Analysis: Understand the drivers of positive and negative feedback or behaviour, and why respondents feel the way they do. - Smart Filtering: Find the stuff you care about - even if people are using varying language to describe the issue. We don’t have to rely on keyword matching to do this!
Key Benefits
When it comes to finding insight in unstructured text, everyone focuses on levels one and two. How they do it has radically changed - Natural Language Processing has found new and exciting ways to establish sentiment and categorise data. But the outcomes remain the same - from the biggest megacorp to the edgiest startup, you’re getting general feelings about general categories. Wordnerds uses first and second level analysis a lot. They’re both super-important. But we have the only tool on the market that offers Third Level Insight. We break the data down into topics that allow you to easily understand what’s happening, and crucially, what you can do about it. These topics are completely unsupervised - no training, no waiting. It’s just there for you, from the first time you add your data to the platform. We recently had a demo with a major UK retailer. They’d given us some data, and asked us what they should do. They’d looked all across the market, trying to establish what the issue was. The had been given the same answer by all of these tools: 1st level insight: There’s a problem with delivery. 2nd level insight: It's a delivery issue regarding flowers But Wordnerds was the only tool which could give the third level insight: 3rd level insight: It's a delivery issue regarding flowers, involving water leaking from the plastic bag causing the cardboard box to deteriorate That’s the difference between Wordnerds and everyone else. Even Google can’t extract the insight that Wordnerds can from written language.
Applications
Many of our existing customers are using the Wordnerds platform to: - Identify trends - what new topics are being surfaced day to day? Are people boycotting a particular product due to it being tested on animals? What new trends are surfacing when compared to other points in time? Our platform identifies trending topics by finding data points that indicate a change in behaviour/sentiment thus surfacing unknown unknowns. This allows us to give clients the best possible chance of being proactive when determining changing consumer behaviour. - Find opportunities in their market - i.e. identify areas where competition is weaker or where customers believe there is room for improvement in order to stand out from the crowd. Find gaps in the market where consumers believe a service or product would help. - Consumer behaviour research and market sizing - identify the pool of potential consumers and how many other brands are competing for their business. - Lead Generation and targeting new audiences - the platform allows us to easily identify consumers who are unhappy with a product/service that they have received from competitors thus allowing clients to reach out and add to their customer base. Across all our projects to date, customers are communicating strong value and returns on their investment through: - An objective understanding of what their stakeholders care about through effective text-analysis - Data-backed decision making - No need for manual tagging - saving hours and reducing subjectivity/human error - Real-time view of customer sentiment and feedback - Automated reporting - Clear, easy to understand visualisations of the data, which can be shared with the wider organisation