1 Ocak 2022 Konferans bildirisi Açık Erişim

Beyhan, Fatih; Carik, Buse; Arin, Inanc; Terzioglu, Aysecan; Yanikoglu, Berrin; Yeniterzi, Reyyan

JSON

{
  "conceptdoi": "10.48623/aperta.254118", 
  "conceptrecid": "254118", 
  "created": "2023-07-28T20:22:45.720532+00:00", 
  "doi": "10.48623/aperta.254119", 
  "files": [
    {
      "bucket": "32b2c34f-da43-4d4f-9a3e-d6b04d69b49c", 
      "checksum": "md5:5a7e3b04a00c45437d3bc4bccd758efb", 
      "key": "bib-d5f4c445-9f64-45de-b278-e1e8571774f4.txt", 
      "links": {
        "self": "https://aperta.ulakbim.gov.tr/api/files/32b2c34f-da43-4d4f-9a3e-d6b04d69b49c/bib-d5f4c445-9f64-45de-b278-e1e8571774f4.txt"
      }, 
      "size": 219, 
      "type": "txt"
    }
  ], 
  "id": 254119, 
  "links": {
    "badge": "https://aperta.ulakbim.gov.tr/badge/doi/10.48623/aperta.254119.svg", 
    "bucket": "https://aperta.ulakbim.gov.tr/api/files/32b2c34f-da43-4d4f-9a3e-d6b04d69b49c", 
    "conceptbadge": "https://aperta.ulakbim.gov.tr/badge/doi/10.48623/aperta.254118.svg", 
    "conceptdoi": "https://doi.org/10.48623/aperta.254118", 
    "doi": "https://doi.org/10.48623/aperta.254119", 
    "html": "https://aperta.ulakbim.gov.tr/record/254119", 
    "latest": "https://aperta.ulakbim.gov.tr/api/records/254119", 
    "latest_html": "https://aperta.ulakbim.gov.tr/record/254119"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "tubitak-destekli-proje-yayinlari"
      }
    ], 
    "creators": [
      {
        "name": "Beyhan, Fatih"
      }, 
      {
        "name": "Carik, Buse"
      }, 
      {
        "name": "Arin, Inanc"
      }, 
      {
        "affiliation": "Sabanci Univ, Fac Arts & Social Sci, TR-34956 Istanbul, Turkey", 
        "name": "Terzioglu, Aysecan"
      }, 
      {
        "name": "Yanikoglu, Berrin"
      }, 
      {
        "name": "Yeniterzi, Reyyan"
      }
    ], 
    "description": "Social media posts containing hate speech are reproduced and redistributed at an accelerated pace, reaching greater audiences at a higher speed. We present a machine learning system for automatic detection of hate speech in Turkish, along with a hate speech dataset consisting of tweets collected in two separate domains. We first adopted a definition for hate speech that is in line with our goals and amenable to easy annotation; then designed the annotation schema for annotating the collected tweets. The Istanbul Convention dataset consists of tweets posted following the withdrawal of Turkey from the Istanbul Convention. The Refugees dataset was created by collecting tweets about immigrants by filtering based on commonly used keywords related to immigrants. Finally, we have developed a hate speech detection system using the transformer architecture (BERTurk), to be used as a baseline for the collected dataset. The binary classification accuracy is 77% when the system is evaluated using 5-fold cross validation on the Istanbul Convention dataset and 71% for the Refugee dataset. We also tested a regression model with 0.66 and 0.83 RMSE on a scale of [0-4], for the Istanbul Convention and Refugees datasets.", 
    "doi": "10.48623/aperta.254119", 
    "has_grant": false, 
    "license": {
      "id": "cc-by"
    }, 
    "meeting": {
      "title": "LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION"
    }, 
    "publication_date": "2022-01-01", 
    "related_identifiers": [
      {
        "identifier": "10.48623/aperta.254118", 
        "relation": "isVersionOf", 
        "scheme": "doi"
      }
    ], 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "254119"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "254118"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "conferencepaper", 
      "title": "Konferans bildirisi", 
      "type": "publication"
    }, 
    "science_branches": [
      "Di\u011fer"
    ], 
    "title": "A Turkish Hate Speech Dataset and Detection System"
  }, 
  "owners": [
    1
  ], 
  "revision": 1, 
  "stats": {
    "downloads": 9.0, 
    "unique_downloads": 9.0, 
    "unique_views": 46.0, 
    "version_downloads": 9.0, 
    "version_unique_downloads": 9.0, 
    "version_unique_views": 44.0, 
    "version_views": 46.0, 
    "version_volume": 1971.0, 
    "views": 49.0, 
    "volume": 1971.0
  }, 
  "updated": "2023-07-28T20:22:45.783929+00:00"
}