So Basically, I want to create a query recommendation system which recommends to the user a set of queries, the answer set of which contains data that are of interest to the user. A query that is recommended for a user is a query that the specific user has not posed to the database in the past and is expected that if posed, the user will give a high score. Note that although the query may have not been posed by the specific user in the past, some of its tuples may have in the past been seen by the user, maybe because they were in the answer set of another query that the user has posed.
Any suggestions would be highly appreciated.
Thank you so much.
Assuming that the user already put in a couple of query words, you could in a first step tryo to find out in what relationships these words are. For example, if the words are antonyms, you could suggest "what is the difference between * and *". You will need something like an ontology.
Regards,
Joachim
https://realpython.com/build-recommendation-engine-collaborative-filtering/
- Badges
- Science topic
- Similar topics
- Biological Science
- Biochemistry
- Enzymology
- Enzymes