System and method for mining category aspect information

A system comprising:

• one or more hardware processors configured to at least:
• access a table comprising joined data, the joined data including historical data comprising data based on actions performed by users, listing data comprising data describing each listing, and a determined category for each listing;
• determine demand scores based on the joined data;
• determine at least one most relevant aspect name for a category based on the determined demand scores;
• and
• in response to an indication that a user is creating a new listing within the category, transmit a message for display on a device of the user, the message indicating the at least one most relevant aspect name for the category and suggesting the user provide an aspect value that corresponds to the at least one most relevant aspect name to be included in the new listing.

A machine-readable storage medium having no transitory signals and storing instructions which, when executed by at least one processor of a machine, cause the machine to perform operations comprising:

• accessing a table comprising joined data, the joined data including historical data comprising data based on actions performed by users, listing data comprising data describing each listing, and a determined category for each listing;
• determining demand scores based on the joined data;
• determining at least one most relevant aspect name for a category based on the determined demand scores;
• and
• in response to an indication that a user is creating a new listing within the category, transmitting a message for display on a device of the user, the message indicating the at least one most relevant aspect name for the category and suggesting the user provide an aspect value that corresponds to the at least one most relevant aspect name to be included in the new listing.