Urban Dreams of Migrants: A Case Study of Migrant Integration in Shanghai
Authors: Yang Yang, Chenhao Tan, Zongtao Liu, Fei Wu, Yueting Zhuang
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To investigate the process of migrant integration, we employ a one-month complete dataset of telecommunication metadata in Shanghai with 54 million users and 698 million call logs. ...Our classifier is able to achieve an F1-score of 0.82 when distinguishing settled migrants from locals... |
| Researcher Affiliation | Academia | Yang Yang, Chenhao Tan, Zongtao Liu, Fei Wu, Yueting Zhuang College of Computer Science and Technology, Zhejiang University, China Department of Computer Science, University of Colorado Boulder, USA yangya@zju.edu.cn, chenhao@chenhaot.com, {tomstream, wufei, yzhuang}@zju.edu.cn |
| Pseudocode | No | The paper describes methods in prose, tables, and figures, but no explicit pseudocode or algorithm blocks are provided. |
| Open Source Code | No | The paper does not contain any statement about releasing source code or a link to a code repository. |
| Open Datasets | No | Our dataset contains complete telecommunication records between mobile users using China Telecom in Shanghai, spanning a month from September 3rd, 2016, to September 30th, 2016 (four weeks). The data is provided by China Telecom, the third largest mobile service provider in China. |
| Dataset Splits | No | We randomly draw 50% of users and use their calling logs in week 2 to train the classifier. The remaining data is used to test the classifier (50% of data in week 2, and 100% of data in week 3 and week 4). ...We choose the best ℓ2 penalty coefficient using 5-fold cross-validation in training data. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for experiments. |
| Software Dependencies | No | The paper states 'We use ℓ2-regularized logistic regression' for the classifier but provides no specific software version numbers for any tools, libraries, or programming languages used. |
| Experiment Setup | Yes | We choose the best ℓ2 penalty coefficient using 5-fold cross-validation in training data. |