Toward Word Embedding for Personalized Information Retrieval

Nawal Ould Amer (1, 2, 3) , Philippe Mulhem (1) , Mathias Géry (2)

1 LIG - Laboratoire d'Informatique de Grenoble
2 LHC - Laboratoire Hubert Curien
3 MRIM - Modélisation et Recherche d’Information Multimédia [Grenoble]

This paper presents preliminary works on using Word Embedding (word2vec) for query expansion in the context of Personalized Information Retrieval. Traditionally, word em-beddings 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.

Keywords: Word Embedding; word2vec; Personalization; Social Book Search; Query expansion

Domains: Information Retrieval [cs.IR]

Nawal Ould Amer, Philippe Mulhem, Mathias Géry. Toward Word Embedding for Personalized Information Retrieval. Neu-IR: The SIGIR 2016 Workshop on Neural Information Retrieval, Jul 2016, Pisa, Italy. ⟨ujm-01377080⟩