Improving Query Safety at Pinterest

TL;DR

This paper introduces PinSets, a system that effectively expands small seed sets of queries into large, diverse, and precise collections to identify unsafe queries, significantly reducing unsafe suggestions at Pinterest.

Contribution

PinSets is a novel hybrid system combining textual and behavioral data to accurately expand query sets for safety detection, handling linguistic diversity and ambiguity.

Findings

Expanded 20 seed queries into 15,670 queries with over 99% precision.

Decreased unsafe query suggestions at Pinterest by 90%.

Effectively handles slang, typos, and ambiguous words.

Abstract

Query recommendations in search engines is a double edged sword, with undeniable benefits but potential of harm. Identifying unsafe queries is necessary to protect users from inappropriate query suggestions. However, identifying these is non-trivial because of the linguistic diversity resulting from large vocabularies, social-group-specific slang and typos, and because the inappropriateness of a term depends on the context. Here we formulate the problem as query-set expansion, where we are given a small and potentially biased seed set and the aim is to identify a diverse set of semantically related queries. We present PinSets, a system for query-set expansion, which applies a simple yet powerful mechanism to search user sessions, expanding a tiny seed set into thousands of related queries at nearly perfect precision, deep into the tail, along with explanations that are easy to interpret. PinSets owes its high quality expansion to using a hybrid of textual and behavioral techniques (i.e., treating queries both as compositional and as black boxes). Experiments show that, for the domain of drugs-related queries, PinSets expands 20 seed queries into 15,670 positive training examples at over 99\% precision. The generated expansions have diverse vocabulary and correctly handles words with ambiguous safety. PinSets decreased unsafe query suggestions at Pinterest by 90\%.