260 likes | 281 Views
WordStat and Yoshikoder are powerful text analysis tools designed to process various forms of text data, including open-ended responses, journal articles, and electronic communications. With features such as KWIC analysis and statistical computations, these tools allow users to extract valuable insights from their data. WordStat also offers the ability to build customized dictionaries, while Yoshikoder supports cross-platform analysis and the importing of outside dictionaries. Both tools provide easy export of results to Excel for further analysis.
E N D
WordStat & Yoshikoder T.M. & M.S.
About WordStat • Must be run as part of SimStat • Designed to process text such as open ended responses, journal articles, electronic communications, etc. • Standard dictionaries are lacking, it is fairly easy to build your own dictionary • Includes KWIC (Key Word In Context) • Includes statistical computations
Preparing Data • Use spell-check, because misspelled words may be left uncoded by WordStat • WordStat is NOT case sensitive by default, but that can be modified • You can choose to include cases with missing values, or not • Data has to be in form of a spreadsheet • Columns = variables • Rows = cases
Yoshikoder: Overview • Can be downloaded free at www.yoshikoder.org • A cross-platform, multi-lingual CATA program • Analyzes any text (.txt) document in ASCII, Unicode (UTF-8), or national encodings (e.g. Big5 Chinese.) • Must run one case at a time • Can import LIWC and other outside dictionaries • May write your own dictionary • Exports results into Excel
Yoshikoder: The text • Blogs from 5 male and 5 female MySpace users were analyzed using 8 LIWC dictionaries: • “I” references • “Job” references • “Leisure” references • “Occupation” references • References to “Self” • “Social” references • “We” references to group • “You” references to other
Yoshikoder: Output Output is exported directly into Excel:
Yoshikoder: Results • Analyzed difference between gender groups using ANOVA • We found no significant differences.
Concordances • A concordance is a representation of one or more patterns with their respective context in the document. • Concordances are arranged in a 3-column table, with the target word in the middle and the text to the left and right.
Document Reports • Word frequency report – shows how many times the word appears in the document and the relative proportion of the text the word takes up. • Presented in a table format
Dictionary Reports • Applies dictionary to entire document • Results presented in a table format • If you only want to look at statistics of categories simply check the ‘hide pattern’ box.
Report on all Documents • To gather a report on the word frequency of all documents at once click on: Reports > All Word Frequencies • For a report on just one document click on: Reports > Document Word Frequencies
Compare Documents • Yoshikoder allows the user to compare two documents with respect to a dictionary. • To compare documents, click on: Reports > Document Comparison
Acceptable File Types • Yoshikoder accepts .txt files. • Yoshikoder Converter can translate Word and pdf files to .txt in order to be analyzed. This can be downloaded at http://www.yoshikoder.org/ykconverter/