Combining Heterogenous Social and Geographical Information for Event Recommendation
Authors: Zhi Qiao, Peng Zhang, Yanan Cao, Chuan Zhou, Li Guo, Binxing Fang
AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on real-world data sets show the performance of our method. and Experiments We implement the proposed recommendation model and test on several real-world data sets to demonstrate its effectiveness. |
| Researcher Affiliation | Academia | 1Institute of Computing Technology of the Chinese Academy of Sciences 2Institute of Information Engineering, Chinese Academy of Sciences 3University of the Chinese Academy of Sciences |
| Pseudocode | Yes | Algorithm 1: The algorithm of He Sig |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | The data sets are extracted from the work (Liu et al. 2012). |
| Dataset Splits | Yes | For all the five data sets, we use 5-fold crossvalidation for performance assessment, and we report the average results. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run the experiments. |
| Software Dependencies | No | The paper does not specify version numbers for any software dependencies or libraries used in the implementation or experiments. |
| Experiment Setup | Yes | Learning rate controls the speed of model training. However, it may not be able to converge if it is set too large. In this work, the learning rate is set to 0.001 for both matrix factorizations: geographical and personal. On the other hand, regularization parameters are also empirically set to 0.001 for all. and Empirically, we set the number of dimensions to be 10 for the latent factors in our model. Similar situation occurs in setting the number of reginal clusters. Empirically, we set the number to be 20 for each city s data. |