Hello Team,
In Appian we have a Inbuilt function for sentiment score calculation for Text .
"a!sentimentScore() " - only for text.
And we do have Google Cloud Natural Language connected system to perform entity and sentiment analysis to collect information from HTML or plain text.
But,my question is how do we calculate sentiment score based on voice. if the person who is taking Interview , how his voice is analyzed and get Sentiment score.
Could you please help me in understanding How sentiment score calculate for Voice in Appian.
Regards,
J Vinay.
Discussion posts and replies are publicly visible
There is no OOTB way of doing this. But you could use a external voice-to-text service and feed the result into a!sentimentScore().
Ok got it.
Thank you Stefan, for a Quick Reply.
HI Stefan,
there is recording saved locally now i have to send that file to the external service to get text from that , how could i send that recording file to external service ?
I assume that this service has an API. Use that.
Appian's inbuilt a!sentimentScore() function and the Google Cloud Natural Language connected system are designed to analyze text data to calculate sentiment scores. However, analyzing sentiment in voice data is a different task that requires a different approach.
One way to calculate sentiment scores based on voice data is to use speech-to-text technology to transcribe the voice data into text and then use the a!sentimentScore() function or the Google Cloud Natural Language connected system to calculate the sentiment score. There are various speech-to-text APIs available that can be integrated with Appian to transcribe voice data into text.
Another approach is to use speech analysis tools or emotion recognition software that can analyze voice data to detect emotions, tone, and sentiment. There are various third-party tools available that can be integrated with Appian to perform speech analysis on voice data.
It's worth noting that analyzing sentiment in voice data can be more challenging than analyzing sentiment in text data due to variations in tone, intonation, and context. The accuracy of sentiment analysis results may also vary based on factors such as the quality of the voice recording and the performance of the speech analysis tools used.
Rachel Gomez