Resumen
Keyword extraction is a critical task that enables various applications, including text classification, sentiment analysis, and information retrieval. However, the lack of a suitable dataset for semantic analysis of keyword extraction remains a serious problem that hinders progress in this field. Although some datasets exist for this task, they may not be representative, diverse, or of high quality, leading to suboptimal performance, inaccurate results, and reduced efficiency. To address this issue, we conducted a study to identify a suitable dataset for keyword extraction based on three key factors: dataset structure, complexity, and quality. The structure of a dataset should contain real-time data that is easily accessible and readable. The complexity should also reflect the diversity of sentences and their distribution in real-world scenarios. Finally, the quality of the dataset is a crucial factor in selecting a suitable dataset for keyword extraction. The quality depends on its accuracy, consistency, and completeness. The dataset should be annotated with high-quality labels that accurately reflect the keywords in the text. It should also be complete, with enough examples to accurately evaluate the performance of keyword extraction algorithms. Consistency in annotations is also essential, ensuring that the dataset is reliable and useful for further research.