aboutsummaryrefslogtreecommitdiff
path: root/public/about.html
diff options
context:
space:
mode:
authorKumar Damani <me@kumardamani.net>2024-08-14 20:03:45 +0000
committerKumar Damani <me@kumardamani.net>2024-08-14 20:03:45 +0000
commitcd66828ed8bc688491194db98a1e8fc3499058d4 (patch)
tree82a1edc3b8052a999247bec3e19fc9c230b51e75 /public/about.html
parent9a9c187d9b21500f6fd248a3a69c3ec5b70b32b1 (diff)
moved stuff around
Diffstat (limited to 'public/about.html')
-rw-r--r--public/about.html42
1 files changed, 42 insertions, 0 deletions
diff --git a/public/about.html b/public/about.html
new file mode 100644
index 0000000..138d1e9
--- /dev/null
+++ b/public/about.html
@@ -0,0 +1,42 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+ <title>Name my Dragon - About</title>
+ <link rel="stylesheet" href="style.css">
+</head>
+<body>
+ <center>
+ <h1>How it works</h1>
+ <div class="container">
+ <img class="flex" src="images/pixel-lasso.jpeg" max-width="50%" alt="Pixel art of a cowboy lassoing a dragon.">
+ <div class="flex flex2" style="max-width: 500px; color: unset;">
+ <p>
+ This site uses word similarity to score all dragon names from George R.R. Martin's
+ <a href="https://en.wikipedia.org/wiki/Game_of_Thrones" target="_blank">A Song of Ice and Fire</a>
+ universe in terms of their "closeness" to the given name.
+ The dragon name that is the "closest" is the one selected as the user's dragon.
+ </p>
+ <p>
+ It uses three popular techniques in
+ <a href="https://en.wikipedia.org/wiki/Natural_language_processing" target="_blank">NLP</a>
+ to calculate similarity scores - these are the
+ <a href="https://en.wikipedia.org/wiki/Levenshtein_distance" target="_blank">Levenshtein Distance</a>,
+ <a href="https://en.wikipedia.org/wiki/Cosine_similarity" target="_blank">Cosine Similarity</a>,
+ and <a href="https://en.wikipedia.org/wiki/Jaccard_index" target="_blank">Jaccard Similarity</a>.
+ </p>
+ <p>
+ The final result shown to the user uses cosine similarity only,
+ but top ranking dragons from each of the other two techniques are
+ also shown as alternatives.
+ </p>
+ </div>
+ </div>
+ <footer>
+ <a href="index.html">Home</a><br>
+ <a href="https://kumardamani.net" target="_blank">Author</a>
+ </footer>
+ </center>
+</body>
+</html>