As a participant tells a story, the system can analyze audio, text transcriptions, and physiological signals to determine the overall tone of the story with 83 percent accuracy. Using deep-learning techniques, the system can also provide a “sentiment score” for specific five-second intervals within a conversation.
The more data is analyzed by the system, the more accurate its performance gets. For these tests, subjects wore a Samsung Simband. Movement, heart rate, blood pressure, blood flow, and skin temperature were used in addition to audio data and text transcripts to perform tone and energy analysis. While the algorithm is not perfect yet, it is only going to get better with more data.