27:null 28:["$","title",null,{"children":"How to perform sentiment analysis? | Loren🤑 | Observable"}] 2d:[] 2b:{"id":"c3963c82f3fa9210","slug":null,"title":"How to perform sentiment analysis?","thumbnail":"f45f293411c855244381d2656b942a1b041648346e9c43fa41d58def38fa7b34","access_level":"public","create_time":"$D2023-03-07T18:13:20.896Z","update_time":"$D2023-03-07T18:18:43.173Z","view_time":null,"first_public_time":"$D2023-03-07T18:13:20.896Z","has_unpublished_edits":null,"fork":{"id":"9c583e2da07be119","slug":"how-to-perform-sentiment-analysis","title":"How to perform sentiment analysis?","owner":{"id":"062de6e3e5a0d590","login":"winkjs","name":"WinkJS"}},"stars":0,"starred":false,"owner":{"type":"team","id":"7f0838cc03c1144d","login":"lorenzo-labarta-arilla","name":"Loren🤑","avatar_url":"https://avatars-next.observableusercontent.com/da36f3490167807cba943a572c12f7ebb1458caeb235f4a262c5d47deb200a55","tier":"starter_2024"},"version":98,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"ad86c9f89e3e370a","login":"lorenzo-labarta-arilla","name":"Loren🤑","avatar_url":"https://avatars-next.observableusercontent.com/da36f3490167807cba943a572c12f7ebb1458caeb235f4a262c5d47deb200a55","tier":null}],"members":[{"type":"individual","id":"ad86c9f89e3e370a","login":"lorenzo-labarta-arilla","name":"Loren🤑","avatar_url":"https://avatars-next.observableusercontent.com/da36f3490167807cba943a572c12f7ebb1458caeb235f4a262c5d47deb200a55","tier":null,"role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":1,"collection":null,"type":"notebook","body":{"title":"How to perform sentiment analysis?","cells":[{"id":0,"value":"# How to perform sentiment analysis?","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":23,"value":"md`Sentiment analysis measures the sentiment of a phrase or a document. Typically such a measurement has a value between -1 (negative) to +1(positive), with values near 0 representing neutral sentiment. It has many applications such as judging the overall feedback to an event/product from social media; or in chatbots fine-tuning response by using the sentiment score of utterance. [WinkNLP](https://github.com/winkjs/wink-nlp) measures sentiment using [**its.sentiment**](https://winkjs.org/wink-nlp/its-as-helper.html) helper for the entire document or its sentences.\n\nIn the example below, [markup()](https://winkjs.org/wink-nlp/visualizing-markup.html) method has been used to create color intensity coded visualization of each stanza of a poem:`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":31,"value":"{\n const doc = nlp.readDoc( text );\n doc.sentences()\n .each((s) => \n s.markup(beginTag(s), endTag(s)));\n return html`${''+doc.out(its.markedUpText)+'

Stanza	Score

'}`;\n}","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":4,"value":"md`---`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":7,"value":"md`### Setup`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":10,"value":"winkNLP = (await import('https://cdn.skypack.dev/wink-nlp')).default;","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":13,"value":"model = (await import('https://cdn.skypack.dev/wink-eng-lite-web-model')).default;","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":16,"value":"nlp = winkNLP( model );","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":19,"value":"its = nlp.its;","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":22,"value":"text = `Do not stand at my grave and weep.\nI am not there; I do not sleep.\nI am a thousand winds that blow.\nI am the diamond glints on snow.\nI am the sun on ripened grain.\nI am the gentle autumn rain.\nWhen you awaken in the morning’s hush\nI am the swift uplifting rush\nof quiet birds in circling flight.\nI am the soft star shine at night.\nMy family is deadIn 2019, Barcelona Airport handled a record 52,686,314 million passengers, up 5.0% from 2018 It is a hub for Level and Vueling, and a focus city for Air Europa, Iberia, EasyJet and Ryanair The Barcelona–Madrid air shuttle service, known as \"\"Pont Aeri\"\" or \"\"Puente Aéreo\"\", literally \"\"Air Bridge\"\", was the world's busiest route until 2008, with the highest number of flight operations in 2007 The schedule has been reduced since February 2008, when a Madrid–Barcelona high-speed rail line was opened, covering the distance in 2 hours 30 minutes, and quickly became popular.\nI am not there; I did not die.`;","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":66,"value":"beginTag = function ( s ) {\n return ``;\n};","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":73,"value":"endTag = function ( s ) {\n return `${s.out(its.sentiment).toFixed(2)}`;\n};","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"},{"id":58,"value":"md`---\n### About\n[**WinkNLP**](https://winkjs.org/) is a **developer friendly** JavaScript library for Natural Language Processing (NLP). Designed specifically to make development of NLP solutions **easier** and **faster**, winkNLP is optimized for the right balance of performance and accuracy. The package can handle large amount of raw text at speeds **over 525,000 tokens/second** for the **entire NLP pipeline**. And with a **test coverage of ~100%**, [wink-nlp](https://winkjs.org/) is a tool for building production grade systems with confidence.`","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W2d","stdlib":"1","titling":"auto"}} 2c:"$2b:body"