{"id":10965,"date":"2019-05-02T21:15:59","date_gmt":"2019-05-03T00:15:59","guid":{"rendered":"https:\/\/tarciziosilva.com.br\/blog\/?p=10965"},"modified":"2019-05-02T21:38:50","modified_gmt":"2019-05-03T00:38:50","slug":"text-analysis-with-antconc-for-social-media-data-clusters-and-n-grams","status":"publish","type":"post","link":"https:\/\/tarciziosilva.com.br\/blog\/text-analysis-with-antconc-for-social-media-data-clusters-and-n-grams\/","title":{"rendered":"Text Analysis with AntConc for social media data: Clusters and N-Grams"},"content":{"rendered":"

\"\"In the last post, we learn how to explore and analyze concordances in the software\u00a0AntConc<\/strong>. Now we are going to show you how to use AntConc to study clusters, n-grams and also how to count hashtags frequency and locate them.<\/p>\n

This post is part of a series of tutorials:<\/p>\n

    \n
  1. Intro, Opening a File and Settings<\/a><\/li>\n
  2. Word Lists and File Viewer\u00a0<\/a><\/li>\n
  3. Concordancer and Concordance Plot\u00a0<\/a><\/li>\n
  4. Clusters and N-Grams (we are here)<\/li>\n
  5. Collocations\u00a0(soon)<\/li>\n
  6. Keyword Lists\u00a0(soon)<\/li>\n<\/ol>\n

     <\/p>\n

    Extracting N-Grams from the corpora<\/i><\/strong><\/p>\n

    N-Grams are a contiguous sequence of items from a text(s). They can be used as a way to analyze phonemes, letters, syllables or words, for example. To our goals, we are going to see the required steps to generate n-grams of words in a given text.<\/span><\/p>\n

    1. Firstly, as usual, you need to open a file and generate a Word List. This time, we are going to use a corpus of \u00a0thousand tweets containing the term \u2018<\/span>plastic<\/span><\/i>\u2019. Download a <\/span>corpus file with 19k tweets<\/span><\/a>.<\/p>\n

    2.\u00a0<\/span>It\u2019s important that you don\u2019t forget to open the <\/span>customized settings<\/span><\/a>, because we\u2019ll work with #hashtags and @usernames. <\/span><\/p>\n

    3. T<\/span>o use <\/span>N-Grams<\/span><\/i>, you need to go to the tab <\/span>Clusters\/N-Grams<\/span><\/i> and check the option highlighted on the image:<\/span><\/p>\n

    \"\"<\/p>\n

     <\/p>\n

    4. Click and Start and here it is the result<\/span><\/p>\n

    \"\"<\/p>\n

     <\/p>\n

    5. You can change the minimum and maximum values of the N-Gram Size. For example, if you change them to 1 and 3, the result changes and now you can see 1-gram and 3-gram sequences of words:<\/span><\/p>\n

    \"\"<\/p>\n

     <\/p>\n

    6. To analyze specific clusters of words, you can search for them using the Search Term box.<\/span><\/p>\n

    \"\"<\/p>\n

     <\/p>\n

    7.\u00a0Mind the options like <\/span>Search Term Position<\/span><\/i>. You can search for words before or after your terms. Searching for clusters with size 2 with the term <\/span>plastic<\/span><\/i> On Right, we get the following result.<\/span><\/p>\n

    \"\"<\/p>\n

     <\/p>\n

    8. Important: the column <\/span>Range<\/span><\/i> counts the number of Corpus Files that word or term is present. This number is specially interesting when you are comparing corpora.<\/span><\/p>\n

     <\/p>\n

    Counting Hashtags<\/i><\/strong><\/p>\n

    You can use the <\/span>Clusters\/N-Grams<\/span><\/i> tab to count terms that have some structure, character or word in common. For example: #hashtags and @usernames in some social media platforms.<\/span><\/p>\n

    1. Open your file(s). Don\u2019t forget to configure the settings as explained in the tutorial on <\/span>files and settings<\/span><\/a>.<\/span><\/p>\n

    2. Generate a Word List.<\/span><\/p>\n

    3.\u00a0To generate a list of hashtags, for example, you should go in <\/span>Clusters\/N-Grams<\/span><\/i> tab and use the Search Term \u00a0\u00a0\u2018 #* \u2018 , using 1-1 values in the Cluster Size options.<\/span><\/p>\n

    \"\"<\/p>\n

     <\/p>\n

    Troubleshooting: counting hashtags didn\u2019t worked? Probably, AntConc is configured with the default settings, where the \u2018#\u2019 symbol is a wildcard. Check! <\/span><\/p>\n","protected":false},"excerpt":{"rendered":"

    In the last post, we learn how to explore and analyze concordances in the software\u00a0AntConc. Now we are going to show you how to use AntConc to study clusters, n-grams and also how to count hashtags frequency and locate them. This post is part of a series of tutorials: Intro, Opening a File and Settings […]<\/p>\n","protected":false},"author":6,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,108],"tags":[2581,2589,2588,2586,2579],"class_list":["post-10965","post","type-post","status-publish","format-standard","hentry","category-midias-sociais","category-pesquisa","tag-antconc","tag-clusters","tag-n-gram","tag-social-media-corpora","tag-text-analysis"],"_links":{"self":[{"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/posts\/10965","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/comments?post=10965"}],"version-history":[{"count":4,"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/posts\/10965\/revisions"}],"predecessor-version":[{"id":10983,"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/posts\/10965\/revisions\/10983"}],"wp:attachment":[{"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/media?parent=10965"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/categories?post=10965"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/tarciziosilva.com.br\/blog\/wp-json\/wp\/v2\/tags?post=10965"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}