{ "data_id": "43677", "name": "Medium-Articles", "exact_name": "Medium-Articles", "version": 2, "version_label": "v1.0", "description": "Context\nMedium is one of the most famous tools for spreading knowledge about almost any field. It is widely used to published articles on ML, AI, and data science. This dataset is the collection of about 350 articles in such fields. \nContent\nThe dataset contains articles, their title, number of claps it has received, their links and their reading time.\nAcknowledgements\nThis dataset was scraped from Medium. I created a Python script to scrap all the required articles using just their tags from Medium. Check out the script here\nInspiration\nHow to write a good article? How to inform the reader in an interesting way? What sort of title attracts more crowd? How long an article should be?", "format": "arff", "uploader": "Dustin Carrion", "uploader_id": 30123, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-24 07:08:51", "update_comment": null, "last_update": "2022-03-24 07:08:51", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102502\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": "\"link\"", "runs": 0, "suggest": { "input": [ "Medium-Articles", "Context Medium is one of the most famous tools for spreading knowledge about almost any field. It is widely used to published articles on ML, AI, and data science. This dataset is the collection of about 350 articles in such fields. Content The dataset contains articles, their title, number of claps it has received, their links and their reading time. Acknowledgements This dataset was scraped from Medium. I created a Python script to scrap all the required articles using just their tags from Med " ], "weight": 5 }, "qualities": { "NumberOfInstances": 337, "NumberOfFeatures": 5, "NumberOfClasses": null, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 1, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.01483679525222552, "PercentageOfNumericFeatures": 20, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": null, "PercentageOfMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Manufacturing" }, { "uploader": "38960", "tag": "Mathematics" } ], "features": [ { "name": "author", "index": "0", "type": "string", "distinct": "182", "missing": "0" }, { "name": "claps", "index": "1", "type": "string", "distinct": "163", "missing": "0" }, { "name": "reading_time", "index": "2", "type": "numeric", "distinct": "25", "missing": "0", "min": "2", "max": "31", "mean": "10", "stdev": "5" }, { "name": "link", "index": "3", "type": "string", "distinct": "337", "missing": "0", "ignore": "1" }, { "name": "title", "index": "4", "type": "string", "distinct": "230", "missing": "0" }, { "name": "text", "index": "5", "type": "string", "distinct": "230", "missing": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }