content-based filtering
In plain wordsRecommending items that resemble what you already liked, judged by the items' own features, such as a film's genre, cast and plot, rather than by other people's choices.
A recommender systemrecommender system, n.: Software that guesses which songs, products, posts or jobs you are most likely to want and shows those first, as when a video app lines up the next clip or a shop suggests an add-on. approach that recommends items whose attributes resemble those of items a user has liked, using descriptions of the items rather than other users' behavior. Each item is represented by features, such as tf–idf-weighted keywords, genres, metadata or learned embeddingsembedding, n.: A list of numbers that stands for a word, picture or other item, arranged so that similar items get similar lists. It lets a computer measure similarity of meaning as distance. of its text, images or audio; a user profile is built from the features of items the user engaged with, as an aggregate vector or a per-user classifier; and candidates are ranked by similarity to the profile, often cosine similaritycosine similarity, n.: A score from −1 to 1 for how closely two lists of numbers point the same way, ignoring their size. It is the standard test of whether two texts mean similar things.. Because it needs no data from other users, it can recommend a new item as soon as the item is described, easing the item side of the cold start problemcold start problem, n.: The trouble a recommendation system has with brand-new users or items: with no history to learn from, it has little basis for good suggestions., and its suggestions are easy to explain ('because you watched…'). Its weaknesses are over-specialization, since it rarely suggests anything outside a user's established tastes, dependence on feature quality, and the need for some history from each new user. Production systems usually combine it with collaborative filteringcollaborative filtering, n.: Recommending things based on what people with similar tastes liked, without needing to know anything about the things themselves, as in 'people who bought this also bought…'. in hybrid models.
For brand-new podcasts we fall back on content-based filtering over episode transcripts until listening data accumulate.
Origin
Grew out of information filtering and retrieval research of the 1980s and 1990s, which matched incoming documents against standing user profiles. Systems of the 1990s such as Stanford's Fab, described by Marko Balabanović and Yoav Shoham in 1997 as 'content-based, collaborative recommendation', set it against collaborative filtering and combined the two.
Related
- recommender systemrecommender system, n.: Software that guesses which songs, products, posts or jobs you are most likely to want and shows those first, as when a video app lines up the next clip or a shop suggests an add-on.
- collaborative filteringcollaborative filtering, n.: Recommending things based on what people with similar tastes liked, without needing to know anything about the things themselves, as in 'people who bought this also bought…'.
- cold start problemcold start problem, n.: The trouble a recommendation system has with brand-new users or items: with no history to learn from, it has little basis for good suggestions.
- cosine similaritycosine similarity, n.: A score from −1 to 1 for how closely two lists of numbers point the same way, ignoring their size. It is the standard test of whether two texts mean similar things.
- embeddingembedding, n.: A list of numbers that stands for a word, picture or other item, arranged so that similar items get similar lists. It lets a computer measure similarity of meaning as distance.
- information retrievalinformation retrieval, n.: The study and engineering of search: how to organize huge piles of documents so that the few that matter to someone's question can be found and ranked quickly. AI systems rely on it to look things up.
- collaborative filteringcollaborative filtering, n.: Recommending things based on what people with similar tastes liked, without needing to know anything about the things themselves, as in 'people who bought this also bought…'.
Sources
- Balabanović, M. & Shoham, Y. (1997). Fab: Content-Based, Collaborative Recommendation. Communications of the ACM 40(3).
- Pazzani, M. J. & Billsus, D. (2007). Content-Based Recommendation Systems. In The Adaptive Web, LNCS 4321. Springer.
Mentioned in
recommender systemrecommender system, n.: Software that guesses which songs, products, posts or jobs you are most likely to want and shows those first, as when a video app lines up the next clip or a shop suggests an add-on., cold start problemcold start problem, n.: The trouble a recommendation system has with brand-new users or items: with no history to learn from, it has little basis for good suggestions., collaborative filteringcollaborative filtering, n.: Recommending things based on what people with similar tastes liked, without needing to know anything about the things themselves, as in 'people who bought this also bought…'.