Changes

View changes from to

On December 3, 2024 at 9:20:01 AM UTC, admin:

Changed title to 20 newsgroups dataset (previously 20 Newsgroups dataset)

Set author of 20 newsgroups dataset to Othman Benchekroun (previously Nitish Srivastava)

Updated description of 20 newsgroups dataset from
The 20 Newsgroups dataset consists of 18,845 posts taken from the Usenet newsgroup collection. Each post belongs to exactly one newsgroup. Following the preprocessing in [12] and [7], the data was partitioned chronologically into 11,314 training and 7,531 test articles. After removing stopwords and stemming, the 2000 most frequent words in the training set were used to represent the documents.
to
The 20 newsgroups dataset is used as an example in the paper to explain LIME.

Removed the following tags from 20 newsgroups dataset

Added tag 20 newsgroups to 20 newsgroups dataset

Changed value of field defined_in to https://doi.org/10.48550/arXiv.2010.11273 in 20 newsgroups dataset

Changed value of field extra_authors to [{'extra_author': 'Adel Rahimi', 'orcid': ''}, {'extra_author': 'Qini Zhang', 'orcid': ''}, {'extra_author': 'Tetiana Kodliuk', 'orcid': ''}] in 20 newsgroups dataset

Changed value of field citation to [] in 20 newsgroups dataset

Changed value of field landing_page to https://www.kaggle.com/c/newsgroups in 20 newsgroups dataset

Deleted resource Original Metadata from 20 newsgroups dataset

              
    
          
          
        
        
            f 1 { f 1 {
            2   "access_rights": "", 2   "access_rights": "",
            n 3   "author": "Nitish Srivastava", n 3   "author": "Othman Benchekroun",
            4   "author_email": "", 4   "author_email": "",
            n 5   "citation": [ n 5   "citation": [],
            6     "https://doi.org/10.48550/arXiv.1611.05940", 
            7     "https://doi.org/10.1016/j.procs.2015.03.074" 
            8   ], 
            9   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", 6   "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            n 10   "defined_in": "https://doi.org/10.48550/arXiv.1907.04919", n 7   "defined_in": "https://doi.org/10.48550/arXiv.2010.11273",
            11   "doi": "10.57702/f4hmxqob", 8   "doi": "10.57702/f4hmxqob",
            12   "doi_date_published": "2024-11-25", 9   "doi_date_published": "2024-11-25",
            13   "doi_publisher": "TIB", 10   "doi_publisher": "TIB",
            14   "doi_status": true, 11   "doi_status": true,
            15   "domain": "https://service.tib.eu/ldmservice", 12   "domain": "https://service.tib.eu/ldmservice",
            16   "extra_authors": [ 13   "extra_authors": [
            17     { 14     {
            n 18       "extra_author": "Geo\ufb00rey Hinton", n 15       "extra_author": "Adel Rahimi",
            19       "orcid": "" 16       "orcid": ""
            20     }, 17     },
            21     { 18     {
            n 22       "extra_author": "Ruslan Salakhutdinov", n 19       "extra_author": "Qini Zhang",
            20       "orcid": ""
            21     },
            22     {
            23       "extra_author": "Tetiana Kodliuk",
            23       "orcid": "" 24       "orcid": ""
            24     } 25     }
            25   ], 26   ],
            26   "groups": [ 27   "groups": [
            n 27     { n 
            28       "description": "", 
            29       "display_name": "Text Categorization", 
            30       "id": "2d56b907-932f-4618-ba36-d173c05f6275", 
            31       "image_display_url": "", 
            32       "name": "text-categorization", 
            33       "title": "Text Categorization" 
            34     }, 
            35     { 28     {
            36       "description": "", 29       "description": "",
            37       "display_name": "Text Classification", 30       "display_name": "Text Classification",
            38       "id": "0707d099-de73-41dc-85f6-93e4efa6bf14", 31       "id": "0707d099-de73-41dc-85f6-93e4efa6bf14",
            39       "image_display_url": "", 32       "image_display_url": "",
            40       "name": "text-classification", 33       "name": "text-classification",
            41       "title": "Text Classification" 34       "title": "Text Classification"
            42     } 35     }
            43   ], 36   ],
            44   "id": "b283b5ec-82db-496b-b5e7-0e8cde168067", 37   "id": "b283b5ec-82db-496b-b5e7-0e8cde168067",
            45   "isopen": false, 38   "isopen": false,
            n 46   "landing_page":  n 39   "landing_page": "https://www.kaggle.com/c/newsgroups",
            47 "https://www.cs.toronto.edu/~rsalakhu/20Newsgroups.html", 
            48   "license_title": null, 40   "license_title": null,
            49   "link_orkg": "", 41   "link_orkg": "",
            50   "metadata_created": "2024-11-25T14:20:44.770424", 42   "metadata_created": "2024-11-25T14:20:44.770424",
            n 51   "metadata_modified": "2024-12-02T18:03:37.639224", n 43   "metadata_modified": "2024-12-03T09:20:00.866943",
            52   "name": "20-newsgroups-dataset", 44   "name": "20-newsgroups-dataset",
            n 53   "notes": "The 20 Newsgroups dataset consists of 18,845 posts taken  n 45   "notes": "The 20 newsgroups dataset is used as an example in the 
            54 from the Usenet newsgroup collection. Each post belongs to exactly one  46 paper to explain LIME.",
            55 newsgroup. Following the preprocessing in [12] and [7], the data was  
            56 partitioned chronologically into 11,314 training and 7,531 test  
            57 articles. After removing stopwords and stemming, the 2000 most  
            58 frequent words in the training set were used to represent the  
            59 documents.", 
            60   "num_resources": 1, 47   "num_resources": 0,
            61   "num_tags": 8, 48   "num_tags": 2,
            62   "organization": { 49   "organization": {
            63     "approval_status": "approved", 50     "approval_status": "approved",
            64     "created": "2024-11-25T12:11:38.292601", 51     "created": "2024-11-25T12:11:38.292601",
            65     "description": "", 52     "description": "",
            66     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559", 53     "id": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            67     "image_url": "", 54     "image_url": "",
            68     "is_organization": true, 55     "is_organization": true,
            69     "name": "no-organization", 56     "name": "no-organization",
            70     "state": "active", 57     "state": "active",
            71     "title": "No Organization", 58     "title": "No Organization",
            72     "type": "organization" 59     "type": "organization"
            73   }, 60   },
            74   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559", 61   "owner_org": "079d46db-32df-4b48-91f3-0a8bc8f69559",
            75   "private": false, 62   "private": false,
            76   "relationships_as_object": [], 63   "relationships_as_object": [],
            77   "relationships_as_subject": [], 64   "relationships_as_subject": [],
            n 78   "resources": [ n 65   "resources": [],
            79     { 
            80       "cache_last_updated": null, 
            81       "cache_url": null, 
            82       "created": "2024-12-02T18:38:42", 
            83       "data": [ 
            84         "dcterms:title", 
            85         "dcterms:accessRights", 
            86         "dcterms:creator", 
            87         "dcterms:description", 
            88         "dcterms:issued", 
            89         "dcterms:language", 
            90         "dcterms:identifier", 
            91         "dcat:theme", 
            92         "dcterms:type", 
            93         "dcat:keyword", 
            94         "dcat:landingPage", 
            95         "dcterms:hasVersion", 
            96         "dcterms:format", 
            97         "mls:task", 
            98         "datacite:isDescribedBy" 
            99       ], 
            100       "description": "The json representation of the dataset with its  
            101 distributions based on DCAT.", 
            102       "format": "JSON", 
            103       "hash": "", 
            104       "id": "321add24-8e77-45ff-88dd-7e9c58b85439", 
            105       "last_modified": "2024-12-02T18:03:37.631321", 
            106       "metadata_modified": "2024-12-02T18:03:37.642488", 
            107       "mimetype": "application/json", 
            108       "mimetype_inner": null, 
            109       "name": "Original Metadata", 
            110       "package_id": "b283b5ec-82db-496b-b5e7-0e8cde168067", 
            111       "position": 0, 
            112       "resource_type": null, 
            113       "size": 1288, 
            114       "state": "active", 
            115       "url":  
            116 resource/321add24-8e77-45ff-88dd-7e9c58b85439/download/metadata.json", 
            117       "url_type": "upload" 
            118     } 
            119   ], 
            120   "services_used_list": "", 66   "services_used_list": "",
            121   "state": "active", 67   "state": "active",
            122   "tags": [ 68   "tags": [
            123     { 69     {
            n 124       "display_name": "20 Newsgroups", n 70       "display_name": "20 newsgroups",
            125       "id": "e2be3fd7-6c7f-4975-9a58-c6448ed49fe1", 71       "id": "3c350b53-901d-4f63-86ae-e3f4501f805d",
            126       "name": "20 Newsgroups", 72       "name": "20 newsgroups",
            127       "state": "active", 
            128       "vocabulary_id": null 
            129     }, 
            130     { 
            131       "display_name": "Text Categorization", 
            132       "id": "475e53da-3cb9-4954-ae2b-672fb146c8ee", 
            133       "name": "Text Categorization", 
            134       "state": "active", 73       "state": "active",
            135       "vocabulary_id": null 74       "vocabulary_id": null
            136     }, 75     },
            137     { 76     {
            138       "display_name": "Text Classification", 77       "display_name": "Text Classification",
            139       "id": "daa24bd4-9e49-4ef5-870a-f51681ab0a20", 78       "id": "daa24bd4-9e49-4ef5-870a-f51681ab0a20",
            140       "name": "Text Classification", 79       "name": "Text Classification",
            141       "state": "active", 80       "state": "active",
            142       "vocabulary_id": null 81       "vocabulary_id": null
            n 143     }, n 
            144     { 
            145       "display_name": "document representation", 
            146       "id": "9439f346-f33f-4187-a3a7-a24918f80bb4", 
            147       "name": "document representation", 
            148       "state": "active", 
            149       "vocabulary_id": null 
            150     }, 
            151     { 
            152       "display_name": "newsgroups", 
            153       "id": "3a7aba89-6881-4691-a484-0d8566f60351", 
            154       "name": "newsgroups", 
            155       "state": "active", 
            156       "vocabulary_id": null 
            157     }, 
            158     { 
            159       "display_name": "text categorization", 
            160       "id": "de32a8d9-cbad-45c4-afe4-0f707d3a146b", 
            161       "name": "text categorization", 
            162       "state": "active", 
            163       "vocabulary_id": null 
            164     }, 
            165     { 
            166       "display_name": "text classification", 
            167       "id": "98d3b2df-ea96-4826-971b-6c5bf64c999d", 
            168       "name": "text classification", 
            169       "state": "active", 
            170       "vocabulary_id": null 
            171     }, 
            172     { 
            173       "display_name": "topic modeling", 
            174       "id": "6f8aa70c-b1e6-4882-a45f-64a53a8c16a9", 
            175       "name": "topic modeling", 
            176       "state": "active", 
            177       "vocabulary_id": null 
            178     } 82     }
            179   ], 83   ],
            t 180   "title": "20 Newsgroups dataset", t 84   "title": "20 newsgroups dataset",
            181   "type": "dataset", 85   "type": "dataset",
            182   "version": "" 86   "version": ""
            183 } 87 }