POI2Vec: Geographical Latent Representation for Predicting Future Visitors

Authors: Shanshan Feng, Gao Cong, Bo An, Yeow Meng Chee

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct experiments on 2 real-world datasets to demonstrate the superiority of our proposed approach over the state-of-the-art algorithms for both next POI prediction and future user prediction.
Researcher Affiliation Academia Shanshan Feng,1 Gao Cong,2 Bo An,2 Yeow Meng Chee3 1Interdisciplinary Graduate School 2 School of Computer Science and Engineering 3School of Physical and Mathematical Sciences Nanyang Technological University, Singapore {sfeng003@e., gaocong@, boan@, ymchee@}ntu.edu.sg
Pseudocode No The paper describes models and processes using mathematical equations and textual descriptions, but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement about releasing source code or include links to a code repository for the described methodology.
Open Datasets Yes We conduct experiments on two publicly available datasets. The first one is the Foursquare check-ins within Singapore (Yuan et al. 2013a) and the second one is the Gowalla check-ins within Houston (Liu et al. 2013).
Dataset Splits Yes For both datasets, we use the first 90% chronological check-ins as the training set, the 90 95% as the tuning set, and the last 5% as test set.
Hardware Specification No The paper does not provide any specific details regarding the hardware used to run the experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper mentions techniques like "word2vec" but does not specify any software dependencies with version numbers (e.g., Python, TensorFlow, PyTorch versions).
Experiment Setup Yes Based on the tuning set, the number of dimensions D = 200, region size threshold θ = 0.1, learning rate is set at 0.005.