A patent filed by Facebook detailing a proposed meme analysis engine has been uncovered.
Vipin Singh found the patent for “Meme Detection in Digital Chatter Analysis” while reading up on social media. The patent was filed on July 17th of 2015, and details a future system which would analyze memes by language and key words, then distribute them to their intended audience.
The abstract is as follows:
Some embodiments include a method of detecting memes, as “key terms,” in a chatter aggregation in a social networking system. The method can include aggregating user-generated content objects within the social networking system into the chatter aggregation according to a set of filters. A meme analysis engine can define a target group within the chatter aggregation to compare against a background group. The meme analysis engine can extract key terms from textual content of the target group. The meme analysis engine can determine a relevancy rank of a term in the key terms based on an accounting of the term in the textual content of the target group and a linguistic relevance score of the term according to a linguistic model.
The engine works by identifying key terms within a meme, which can be one word or more, separating them from “irrelevant noise terms,” and using this to work out what exactly the meme is about. Key terms are then linked into different demographics, such as age, gender, location, and language. Figure 3 in the patent gives the example of US citizens aged 35-44 who like cars and trucks. Keywords such as “cars”, “Camaro” and “Corvette” are considered relevant to the group, while other frequent terms such as “bad dog” are ignored.
After releasing the memes, the engine can analyze how those users interact with the meme. Using machine learning, the engine should be able to pick up which memes were more successful and which did not do so well, in order to constantly refine and improve itself.
The full patent can be read here.