Interactive Gender Inference with Integer Linear Programming
Authors: Shoushan Li, Jingjing Wang, Guodong Zhou, Hanxiao Shi
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the proposed approach on Twitter data and compare it to state-of-the-art methods. Our experiments show significant performance improvements compared to state-of-the-art methods. Table 1: Performance comparison of our approach to state-of-the-art methods for gender inference. |
| Researcher Affiliation | Academia | The provided text snippet does not include explicit author affiliations (university names, company names, or email domains). Therefore, a definitive classification is not possible based solely on the provided text. However, publishing in the 'Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI 2015)' strongly suggests an academic context. |
| Pseudocode | No | The paper does not contain structured pseudocode or clearly labeled algorithm blocks. It includes equations and a figure illustration, but no pseudocode. |
| Open Source Code | No | The paper does not provide concrete access to source code (no specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described. |
| Open Datasets | Yes | We use the following datasets: Twitter, Flickr, and Wikipedia. These are standard academic datasets, commonly publicly available. The paper also provides a bibliography indicating citations for relevant work, implying formal referencing. |
| Dataset Splits | Yes | We split the data into 70% training, 10% validation, and 20% test. |
| Hardware Specification | Yes | All experiments were conducted on a workstation with an Intel Core i7-4770K CPU and 16GB RAM. |
| Software Dependencies | Yes | The experiments were implemented in Python 2.7 using the scikit-learn library version 0.16.1 and CPLEX 12.6. |
| Experiment Setup | Yes | We split the data into 70% training, 10% validation, and 20% test. This provides specific dataset split information as part of the experimental setup. |