Comments network and semantic analysis

My idea is a system that identifies common topics for each comment, then the system will create a graph that represent the connection between those topics. If some topics are out of the context (usually spam or non-related commentaries), they will be removed. And finally, the user will have to opportunity to follow a “conversation” about a single topic instead many commentaries about many topics.

I build a prototype that is available in:

To use the prototype: First enter any keyword, and then choose a news and you’ll be able to visualize the comments and semantic graph. The red nodes represent high relevant topics to the conversation and the blue ones represent less important topics. And if you click any node, only related comments will be shown in the page’s lower part.

Some screenshots of this tool:

And please, feel free to play with it and any feedback will be appreciated!


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s