Hi -- Better is obviously relative so I can not say for sure without really trying their solution. I do know that most of these providers give you a generic classification like sports, entertainment, technology etc. That does not work for product feedback because you already know what category your product belongs to.
Our machine learning model is trained for different verticals and classification we show is based on how customers commonly talk about given class of product and what themes are more important to them.
To expand a little on the previous answer, existing cloud API's typically fall into one of the following categories:
1) generic NLP classification API's where you need your own large supply of training data and have very little (if any) control over model parameters, or
2) Topic extraction/topic modeling (usually employing LDA), which will simply give a list of potential topics, and will not be able to conform to the set of topics (in our case called "tags") that we have selected.
Because of this, our solution is better at addressing the specific problem of categorizing customer feedback, and allows for more flexibility in how we can collect and manage data.
3 comments
[ 2.7 ms ] story [ 16.1 ms ] threadOur machine learning model is trained for different verticals and classification we show is based on how customers commonly talk about given class of product and what themes are more important to them.
1) generic NLP classification API's where you need your own large supply of training data and have very little (if any) control over model parameters, or
2) Topic extraction/topic modeling (usually employing LDA), which will simply give a list of potential topics, and will not be able to conform to the set of topics (in our case called "tags") that we have selected.
Because of this, our solution is better at addressing the specific problem of categorizing customer feedback, and allows for more flexibility in how we can collect and manage data.