{ "data_id": "43783", "name": "Covid-19-Research-Articles-(NCBI)", "exact_name": "Covid-19-Research-Articles-(NCBI)", "version": 1, "version_label": "v1.0", "description": "Context\nI collected about 1200 Covid-19 research articles from the NCBI.NLM.NIH website to be utilized in ML algorithms\/ Data Analysis such as Sentiment Analysis, Time Series, Recommender System and\/or Classification. \nContent\nlink: URL to the research article\ntitle: research article\nkeywords: words under which the research article is categorized\ndates: publication date online\nabstract: a brief summary of the article (methods hypothesis included)\nconclusion: findings of the research\n**For the sake of time, I left some columns with 'null' String values. It's your choice to filter the values, and use what is more appropriate for your ML model.\n**I didn't include authors\/contributors as it won't serve a purpose in this datasets \nInspiration\nI am interested in knowing the focus of those studies (by analyzing word frequencies) as well as analyzing the volume of publications over time.", "format": "arff", "uploader": "Elif Ceren Gok", "uploader_id": 30125, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-24 10:26:49", "update_comment": null, "last_update": "2022-03-24 10:26:49", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102608\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": "\"link\"", "runs": 0, "suggest": { "input": [ "Covid-19-Research-Articles-(NCBI)", "Context I collected about 1200 Covid-19 research articles from the NCBI.NLM.NIH website to be utilized in ML algorithms\/ Data Analysis such as Sentiment Analysis, Time Series, Recommender System and\/or Classification. Content link: URL to the research article title: research article keywords: words under which the research article is categorized dates: publication date online abstract: a brief summary of the article (methods hypothesis included) conclusion: findings of the research Inspiration I " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1198, "NumberOfFeatures": 5, "NumberOfClasses": null, "NumberOfMissingValues": 1459, "NumberOfInstancesWithMissingValues": 768, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.004173622704507512, "PercentageOfNumericFeatures": 0, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 64.10684474123539, "AutoCorrelation": null, "PercentageOfMissingValues": 24.357262103505843 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Manufacturing" } ], "features": [ { "name": "link", "index": "0", "type": "string", "distinct": "1198", "missing": "0", "ignore": "1" }, { "name": "title", "index": "1", "type": "string", "distinct": "1197", "missing": "0" }, { "name": "keywords", "index": "2", "type": "string", "distinct": "843", "missing": "351" }, { "name": "conclusion", "index": "3", "type": "string", "distinct": "825", "missing": "372" }, { "name": "dates", "index": "4", "type": "string", "distinct": "266", "missing": "319" }, { "name": "abstract", "index": "5", "type": "string", "distinct": "779", "missing": "417" } ], "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 }