Relationship Between Poetic Meter and Meaning in Accentual-Syllabic Verse (data and replication code)

<ul> <li> <p><strong>main.py</strong>: script to train both lda and word2vec models</p> </li> <li> <p><strong>main.ipynb</strong>: Jupyter Notebook containing all the analyses reported in the paper</p> </li> <li> <p><strong>pos.ipynb</strong>: clustering based on frequencies of parts-of-speech</p> </li> <li><strong>corpora</strong>: contains original data for Czech, English, and Dutch poetry in JSON (proprietary German and Russian not included)</li> </ul> <pre><code>{ &lt;= Each item in the following lists corresponds to particular poem and holds: 'words': [] &lt;= list of lemmata found in the poem 'pos_tags': [] &lt;= their POS-tags (Positional Morphological Tags for Czech, MyStem for Russian, TreeTagger tagsets for other corpora) 'meters': [[]] &lt;= list of meters found in poem 'years': [] &lt;= year when poem published (year when author born in case of English) 'n_words': [] &lt;= number of words 'n_lines': [] &lt;= number of lines 'authors': [] &lt;= author of the poem 'titles': [] &lt;= title of the poem 'schemes': [] &lt;= line-ending schemes } </code></pre> <ul> <li><strong>dicts</strong>: contains Gensim dictionary files for all 5 corpora</li> </ul> <ul> <li><strong>fig</strong>: contains all resulting figures</li> </ul> <ul> <li><strong>json</strong> <strong>&gt; metadata:</strong>&nbsp;contains all metadata on poems in particular corpora</li> </ul> <pre><code>{ &lt;= Each item in the following lists corresponds to particular poem and holds: 'meters': [[]] &lt;= list of meters found in poem 'years': [] &lt;= year when poem published (year when author born in case of English) 'n_words': [] &lt;= number of words 'n_lines': [] &lt;= number of lines 'authors': [] &lt;= author of the poem 'titles': [] &lt;= title of the poem } </code></pre> <ul> <li><strong>json &gt; topics:</strong>&nbsp;contains topic probabilities in particular poems</li> </ul> <pre><code>[ &lt;= each item corresponds to particular poem and comprise 100-dimensional dict { 'topic title': its probability in poem } ] </code></pre> <ul> <li><strong>json &gt; pos:</strong>&nbsp;contains POS relative frequencies in particular poems</li> </ul> <pre><code>[ &lt;= each item corresponds to particular poem { 'POS': its frequency } ] </code></pre> <ul> <li><strong>json &gt; w2v:</strong>&nbsp;contains mapping of lemmata and their neighbours in word2vec models</li> </ul> <ul> <li><strong>models</strong>: contains pretrained lda and word2vec models (Gensim)</li> <li><strong>regression</strong>: contains data and code to produce S5_table and S6_fig</li> </ul>