Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Personalized Time-Aware Tag Recommendation
Authors: Keqiang Wang, Yuanyuan Jin, Haofen Wang, Hongwei Peng, Xiaoling Wang
AAAI 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The experimental results show that our proposed model outperforms the state of the art tag recommendation methods in accuracy and has better ability to recommend new tags. |
| Researcher Affiliation | Collaboration | 1International Research Center of Trustworthy Software Shanghai Key Laboratory of Trustworthy Computing East China Normal University, Shanghai, China 2 Shenzhen Gowild Robotics Co. Ltd |
| Pseudocode | Yes | Algorithm 1: An Optimization Algorithm for TAPITF. |
| Open Source Code | No | The paper does not explicitly state that the source code for their methodology is released, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We evaluate the models on the three public data sets Movielens, Last FM and Delicious described in table 1. |
| Dataset Splits | No | We use leave-one-out to split data set into train set and test set, which is that for each user, his tagging records on a certain item are randomly removed from the training set Strain and put into the test set St. |
| Hardware Specification | No | The paper discusses 'running time' (Table 3) but does not provide any specific details about the hardware used for the experiments, such as CPU/GPU models or memory specifications. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x). |
| Experiment Setup | Yes | Latent factor dimension K = 64, regularization factor λ = 0.00005 and learning rate is 0.05. In TAPITF, d = 0.5, time unit is day. Latent factor dimension and regularization factor is the same as PITF. The iteration number of PITF and TAPITF are both 100. |