You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
node.js/Javascript implementation of Dracula - adapted to do deep sentiment analysis using character embeddings.
2
+
A quick way to get "good enough" sentiment analysis into your applications, this package uses character and word-level embeddings and LSTM networks to decide if a given text is either "positive" or "negative".
3
+
4
+
## Installation
5
+
6
+
npm install dracula-sentiment --save
7
+
8
+
## Usage
9
+
10
+
var dracula = require('dracula-sentiment');
11
+
var text = "xoxo cant wait";
12
+
console.log(text, dracula.analyze(text));
13
+
14
+
For best results, remove any non-ascii characters by converting them to their closest equivalents via `unidecode` or something similar.
15
+
16
+
## Testing
17
+
18
+
npm test
19
+
20
+
Tests aren't very extensive at present.
21
+
22
+
## Contributing
23
+
24
+
If you encounter any sentences where the classifiction is obviously wrong, open an issue and we'll work out a way to extend Dracula's training data so that it doesn't happen. Contributions to clean up the code and improve its style and performance are certainly welcome!
0 commit comments