search

fengzhu1 / GA-DTCDR

This is the model in "A Graphical and Attentional Framework for Dual-Target Cross-Domain Recommendation" (IJCAI2020). GA-DTCDR is an optimized model for DTCDR ("DTCDR: A Framework for Dual-Target Cross-Domain Recommendation" in CIKM2019).
GNU General Public License v3.0
67 stars 18 forks source link

doc2vec #4

Closed Littlepijiang closed 2 years ago

Littlepijiang commented 2 years ago

hi！ I want to know why self.model_D2V = None and can u share the codes of doc2vec？

fengzhu1 commented 2 years ago

Hi, you can find the code of doc2vec in "Doc2vec_DoubanDatasets.py".

Littlepijiang commented 2 years ago

Thank you for your reply. I have another question. Does the generation of some subsets such as movie_subset_5 and moviereviews_subset_5 in "Doc2vec_DoubanDatasets.py" have any requests？ and in a subset，the UID2 or user_id whether need to renumber？

fengzhu1 commented 2 years ago

I have preprocessed the ids of users and items in the datasets. So you do not need to renumber the ids of users and items. As for the subsets "movie_subset_5" and "moviereviews_subset_5", I have uploaded the final version of them in "https://www.researchgate.net/publication/350793434_Douban_dataset_ratings_item_details_user_profiles_tags_and_reviews", i.e., xxx_cleaned. You should adjust the corresponding codes in "Doc2vec_DoubanDatasets.py".