Toward Word Embedding for Personalized Information Retrieval
This work addresses personalized information retrieval for users, but it is incremental as it builds on existing word embedding methods with limited reported gains.
The paper tackled the problem of personalizing word embeddings for information retrieval by learning them from user profiles instead of general corpora, and evaluated on the CLEF Social Book Search 2016 collection, with results indicating that further efforts are needed for effective application.
This paper presents preliminary works on using Word Embedding (word2vec) for query expansion in the context of Personalized Information Retrieval. Traditionally, word embeddings are learned on a general corpus, like Wikipedia. In this work we try to personalize the word embeddings learning, by achieving the learning on the user's profile. The word embeddings are then in the same context than the user interests. Our proposal is evaluated on the CLEF Social Book Search 2016 collection. The results obtained show that some efforts should be made in the way to apply Word Embedding in the context of Personalized Information Retrieval.