Our NLP algorithms understand the voice of customer on a big data scale.

From social search to surveys, we analyze vast sets of unstructured, un-contextualized data, decipher the expression, and deliver actionable insights.

Actionable Insights delivered through technology

Our technology is based on a decade of innovation and co-developed with leading researchers from Stanford University. We deliver emotion analytics where simple sentiment technologies just won’t cut it.

Emotion Analytics

Our proprietary technology goes beyond positive/negative to decipher emotions in text, uncovering the ‘human’ in language.

Audience Understanding

We integrate emotion analytics with structured demographic information (e.g., location, age, and gender), resulting in a rich, high-signal dataset.

Right Data

Built for massive scale, our technology automatically ingests vast sets of unstructured data, from Facebook and Twitter to internal surveys, search trends, and forum posts.

Intelligent Baselines

We build statistical profiles for different data sources and benchmark your data against them, enabling you to identify unusual ‘hot spots’ in your data.

Perception Non-technical Whitepaper


Read Whitepaper

Perception Non-technical Whitepaper

Sentiment Analysis vs. Emotion Analytics Whitepaper


Read Whitepaper

Sentiment Analysis vs. Emotion Analytics Whitepaper

Beyond Sentiment

Context-aware emotion modeling for customer insights.

Moritz Sudhof, Senior NLP Engineer and Algorithmic Lead at Kanjoya, manages the development of Kanjoya's sentiment, emotion, and experience modeling technology.

His team, in collaboration with researchers at Stanford University, is leveraging the rich corpus of emotion data from Experience Project to model human expression in language.

Listen to Moritz present at the Symposium this year to learn more about the world beyond sentiment analysis: Context-aware emotion modeling for customer insights.
The experience project difference

Big data foundation for understanding emotion.

Kanjoya owns and operates the largest and most authentic corpus of structured human expression on the web, the Experience Project.

With a linguist's perspective and a statistician's toolbox, we’ve trained our algorithms on this collection of experiences to understand how people talk when they feel certain ways.

From regular English language usage to social conversations riddled with emoticons, colloquialisms, and slang, Kanjoya models the different meanings words can have based on topic and speaker.