Journal article Open Access

Short‐text feature expansion and classification based on nonnegative matrix factorization

Zhang, Ling; Jiang, Wenchao; Zhao, Zhiming


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/714a554e-ec4e-4d88-af61-22549bfa1a54/2020.jounal.intelligentsystems-proof.pdf"
      }, 
      "checksum": "md5:a24372cb312d85cc874d32455e059aee", 
      "bucket": "714a554e-ec4e-4d88-af61-22549bfa1a54", 
      "key": "2020.jounal.intelligentsystems-proof.pdf", 
      "type": "pdf", 
      "size": 985866
    }
  ], 
  "owners": [
    26570
  ], 
  "doi": "10.1002/int.22290", 
  "stats": {
    "version_unique_downloads": 71.0, 
    "unique_views": 126.0, 
    "views": 130.0, 
    "version_views": 130.0, 
    "unique_downloads": 71.0, 
    "version_unique_views": 126.0, 
    "volume": 69996486.0, 
    "version_downloads": 71.0, 
    "downloads": 71.0, 
    "version_volume": 69996486.0
  }, 
  "links": {
    "doi": "https://doi.org/10.1002/int.22290", 
    "latest_html": "https://zenodo.org/record/4042991", 
    "bucket": "https://zenodo.org/api/files/714a554e-ec4e-4d88-af61-22549bfa1a54", 
    "badge": "https://zenodo.org/badge/doi/10.1002/int.22290.svg", 
    "html": "https://zenodo.org/record/4042991", 
    "latest": "https://zenodo.org/api/records/4042991"
  }, 
  "created": "2020-09-22T06:57:10.900073+00:00", 
  "updated": "2021-03-04T22:00:35.087603+00:00", 
  "conceptrecid": "4042990", 
  "revision": 3, 
  "id": 4042991, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.1002/int.22290", 
    "version": "camera ready", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "Short\u2010text feature expansion and classification based on nonnegative matrix factorization", 
    "journal": {
      "pages": "1-15", 
      "title": "Int Journal Intelligent Systems"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "4042990"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4042991"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "862409", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::862409"
        }, 
        "title": "Blue-Cloud: Piloting innovative services for Marine Research & the Blue Economy", 
        "acronym": "Blue Cloud", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "825134", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::825134"
        }, 
        "title": "smART socIal media eCOsytstem in a blockchaiN Federated environment", 
        "acronym": "ARTICONF", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "824068", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::824068"
        }, 
        "title": "ENVironmental Research Infrastructures building Fair services Accessible for society, Innovation and Research", 
        "acronym": "ENVRI-FAIR", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "correlation", 
      "feature extension", 
      "nonnegative matrix factorization", 
      "short text classification"
    ], 
    "publication_date": "2020-09-22", 
    "creators": [
      {
        "affiliation": "Guangdong University of Technology", 
        "name": "Zhang, Ling"
      }, 
      {
        "affiliation": "Guangdong University of Technology", 
        "name": "Jiang, Wenchao"
      }, 
      {
        "orcid": "0000-0002-6717-9418", 
        "affiliation": "University of Amsterdam", 
        "name": "Zhao, Zhiming"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "article", 
      "type": "publication", 
      "title": "Journal article"
    }, 
    "description": "<p>In this paper, a non\u2010negative matrix factorization feature</p>\n\n<p>expansion (NMFFE) approach was proposed to</p>\n\n<p>overcome the feature\u2010sparsity issue when expanding</p>\n\n<p>features of short\u2010text. First, we took the internal relationships</p>\n\n<p>of short texts and words into account when</p>\n\n<p>segmenting words from texts and constructing their</p>\n\n<p>relationship matrix. Second, we utilized the Dual</p>\n\n<p>regularization non\u2010negative matrix tri\u2010factorization</p>\n\n<p>(DNMTF) algorithm to obtain the words clustering</p>\n\n<p>indicator matrix, which was used to get the feature</p>\n\n<p>space by dimensionality reduction methods. Thirdly,</p>\n\n<p>words with close relationship were selected out from</p>\n\n<p>the feature space and added into the short\u2010text to solve</p>\n\n<p>the sparsity issue. The experimental results showed</p>\n\n<p>that the accuracy of short text classification of our</p>\n\n<p>NMFFE algorithm increased 25.77%, 10.89%, and 1.79%</p>\n\n<p>on three data sets: Web snippets, Twitter sports, and</p>\n\n<p>AGnews, respectively compared with the Word2Vec</p>\n\n<p>algorithm and Char\u2010CNN algorithm. It indicated that</p>\n\n<p>the NMFFE algorithm was better than the BOW algorithm</p>\n\n<p>and the Char\u2010CNN algorithm in terms of classification</p>\n\n<p>accuracy and algorithm robustness.</p>"
  }
}
130
71
views
downloads
Views 130
Downloads 71
Data volume 70.0 MB
Unique views 126
Unique downloads 71

Share

Cite as