Chat and messaging conversations are more than just a string of words. Behind every word choice, typo, phrase, or pause in a conversation have hidden meanings and ‘body language’ that can reveal things about us. People over time, hone these insights, which we call EQ or intuition. But we’re limited in our ability to simultaneously listen, remember and analyze every datapoint in a way machines and AI can. This limits our ability to fully capture everything that’s communicated in a conversation. That’s why we built our messaging analytics and AI platform.
Our analytics engine can generate every datapoint imaginable from a messaging conversation. Coupled with the millions of conversations and labels from users, we built AI to predict hundreds of insights just from a small snippet of a given conversation. These insights include demographics (e.g. age/sex), relationship type (e.g. romantic/ friendly/professional), relationship (e.g. a parent vs. a sibling), moods, interests and personalities.
These insights will be important in building chatbots and conversational AI with human-level intelligence. Just like how you can estimate the age of someone you’re talking to, our AI can predict age range from emoji usage alone. ChatGPT and bots built from language AI models may have 200 IQ, but almost 0 EQ. Most have never trained from actual chat data, so they have no idea how people ACTUALLY talk to each other. Having EQ, or insights about people, are critical in crafting messages that can get through to the human on the other side. In any conversation, it’s not just what you say, but how you say it.
Anyone looking to work on this should contact us at email@example.com. There’s no point in reinventing the wheel.
Here’s just a small sample of analytics/AI engine that underlies our products.
Each message has metadata that can be more revealing than the words themselves. This can be studied over time to establish a baseline pattern, identify trends and even pinpoint the day when things changed.
Word Cloud - Top Things On Your Mind
Personality & Similarity (In-App)
While most of our analytics happen behind the scenes, we provide insights in our apps that users can act on