25 datasets found

Precise user modeling is critical for online personalized recommen-der services. Generally, users’ interests are diverse and are not limited to a single aspect, which is...

The bAbI Movie Dialog dataset is a synthetic dataset containing elementary tasks such as selecting an answer between one or more candidate facts, answering yes/no questions,...

The Amazon dataset is used to evaluate the performance of the proposed approach. It consists of 2000 users, 1500 items, 86690 reviews, 7219 number ratings, 3.6113 average number...

A simplified simulated dataset showing varying user preferences over time and how this can be evaluated with static and dynamic learning algorithms.

The dataset used for term clustering to build a modular ontology according to core ontology from domain-specific text.

Recommender Systems FeedbackLog

The proposed model combines recurrent user history representation with a mixture density network, where a novel attention-based recurrent mixture density has been proposed to...

The Epinions dataset is a large-scale opinion mining dataset. It contains 1 million user-item interactions and is widely used for evaluating the performance of recommender systems.

Million Song Dataset is a collection of audio features and metadata for a million contemporary pop songs. Instead of storing any audio, the dataset consists of features derived...

The Movielens Tag Genome dataset contains 3952 movies, 6040 users and 1 million ratings.

The MART dataset contains 500 art pieces by professional artists and 10 thousand ratings by 100 people (74 females, ages 18–65).

The dataset used in the paper is a collection of explicit interactions gathered from various sources, including music websites, movie ratings, book clubs, social networks, and...

The Yahoo dataset used for training and testing the proposed model, containing leaked passwords.

The KuaiRec-big dataset is a recommender system dataset jointly released by the University of Science and Technology of China and the Kuaishou Community Science Research...

The dataset used in the paper is a user-item bipartite graph, where each user and item is represented as a node, and the edges between them represent the interactions between...

The Yelp dataset challenge contains reviews and images of restaurants, with the goal of recommending images for each review.

Click-Through Rate (CTR) prediction plays a core role in recommender systems, serving as the final-stage filter to rank items for a user. The key to addressing the CTR task is...

The MovieLens dataset contains questions answerable using Wikidata as the knowledge graph, focusing on questions with a single entity and relation.

The dataset is a movie review dataset with five types of nodes (movie, director, tag, writer, and user) and four types of edges (movie-director relation, movie-tag relation,...

The dataset used in the paper is a series of datasets introduced in [46], comprising large corpora of product reviews crawled from Amazon.com. Top-level product categories on...