It’s not just Netflix that’s taking search seriously through the use of recommendations. Pinterest is amping up its search capabilities to provide better results based on the words a user is searching for in relation to what other people may be searching for, the company detailed in a blog post on Monday.
Dong Wang, the Pinterest software engineer who wrote the post, explained that even though a user may search for the word “turkey,” it’s unclear what exactly that person may be looking for. Does he want to find turkey recipes, is he planning a trip to Turkey or is he just interested in poultry — it’s hard to say without some context.
If that person decides to search for “turkey recipes” as part of his next query, Pinterest takes that into account and can assume that the next person who may be searching for “turkey” might also be craving some turkey recipes as well; maybe it’s holiday season and everyone’s hungry. Pinterest learned that “the information extracted from previous query log has shown to be effective in understanding the user’s search intent” and this can be applied to other Pinterest users as well.
Pinterest uses a data-collection workflow called QueryJoin that helps with applying one user’s search queries and the data gleaned from those searches to other users in order to generate more relevant search results for everyone involved. QueryJoin contains data like search queries, demographic statistics, adjacent queries and pins.
Here’s some technical details on QueryJoin, per the blog post:
[blockquote person=”Pinterest” attribution=”Pinterest”]For each Pin, we have aggregated data from the PinJoin (the data collection of a cluster of Pins with the same image signature and the information about those Pins) as well as some engagement stats like the number of clicks, repins and likes.][/blockquote]
The data collected by QueryJoin is used in several Pinterest search functions such as autocomplete, guided search and search relevance.