Facebook’s new Graph Search feature may benefit from upcoming upgrades. When Graph Search was first released, the feature relied primarily on “likes” and check-ins to provide results, but these are ineffective tools since most people do not check-in when they go to places they like, and others like pages ironically rather than honestly. But bringing in further analysis of comments of posts could help improve the accuracy of Graph Search.

Facebook could also integrate Graph Search with Open Graph, Facebook’s system to help “understand the products, services, or other entities described on Web pages and in mobile apps,” reports Technology Review. Open Graph would allow Facebook to understand more than just “likes” and check-ins because it could also link to services like Spotify and analyze musical interests.

An improvement to the Bing search engine has highlighted the potential of searching through Facebook comments. The search engine can search through photo comments and bring more complete search results to the user.

Startup company Trove has also proven the power of search across multiple platforms, as its software shows how “a search for ‘puppy photos’ might reveal an unlabeled Instagram photo of a dog because the photo elicited a tweet using the word ‘dog’ and a Facebook comment saying ‘adorable!'” explains the article.

“However, [entrepreneur Matthew] Berk predicts that Facebook will face challenges taming ‘noise’ that pollutes the Open Graph, because contributors don’t describe their content in a consistent way. It’s a problem that also troubles Graph Search, which has made it abundantly clear that on Facebook, ‘like’ doesn’t always mean you really like something.”