如何從文本中刪除所有停用詞？

Question

我想使用這個JavaScript代碼：

var aStopWords = new Array ("a", "the", "blah"...); 

(code to make it run, full code can be found here: https://jsfiddle.net/j2kbpdjr/) 

// sText is the body of text that the keywords are being extracted from. 
// It's being separated into an array of words. 

// remove stop words 
for (var m = 0; m < aStopWords.length; m++) { 
    sText = sText.replace(' ' + aStopWords[m] + ' ', ' '); 
} 

從文本的身體得到的關鍵字。它工作得很好，但是，我遇到的問題是，它似乎只是遍歷並忽略數組aStopWords中的單詞的一個實例。

所以，如果我有文字的以下機身：

how are you today? Are you well?

我把var aStopWords = new Array("are","well")的話，好像它會忽略的are一審，但仍顯示第二are作爲關鍵字。而它會從關鍵字中完全刪除/忽略well。

如果有人能夠幫助忽略關鍵字aStopWords中所有單詞的實例，我將不勝感激。

Answer 1

你可以很容易地做到這一點。

首先，它將文本分割成關鍵字。然後，它會遍歷所有關鍵字。在經歷時，它會檢查它是否是一個停用詞。如果是這樣，它將被忽略。否則，result對象中該關鍵字的出現次數將會增加。

然後，關鍵字是在以下形式的JavaScript對象：

{ "this": 1, "that": 2 } 

對象是不可排序在JavaScript中，但數組是。所以，重映射到以下結構是必要的：

[ 
    { "keyword": "this", "counter": 1 }, 
    { "keyword": "that", "counter": 2 } 
] 

然後，該陣列可以通過使用counter屬性進行排序。使用slice()函數，只能從排序列表中提取前X個值。

var stopwords = ["about", "all", "alone", "also", "am", "and", "as", "at", "because", "before", "beside", "besides", "between", "but", "by", "etc", "for", "i", "of", "on", "other", "others", "so", "than", "that", "though", "to", "too", "trough", "until"]; 
 
var text = document.getElementById("main").innerHTML; 
 

 
var keywords = text.split(/[\s\.;:"]+/); 
 
var keywordsAndCounter = {}; 
 
for(var i=0; i<keywords.length; i++) { 
 
    var keyword = keywords[i]; 
 
    
 
    // keyword is not a stopword and not empty 
 
    if(stopwords.indexOf(keyword.toLowerCase()) === -1 && keyword !== "") { 
 
    if(!keywordsAndCounter[keyword]) { 
 
     keywordsAndCounter[keyword] = 0; 
 
    } 
 
    keywordsAndCounter[keyword]++; 
 
    } 
 
} 
 

 
// remap from { keyword: counter, keyword2: counter2, ... } to [{ "keyword": keyword, "counter": counter }, {...} ] to make it sortable 
 
var result = []; 
 
var nonStopKeywords = Object.keys(keywordsAndCounter); 
 
for(var i=0; i<nonStopKeywords.length; i++) { 
 
    var keyword = nonStopKeywords[i]; 
 
    result.push({ "keyword": keyword, "counter": keywordsAndCounter[keyword] }); 
 
} 
 

 
// sort the values according to the number of the counter 
 
result.sort(function(a, b) { 
 
    return b.counter - a.counter; 
 
}); 
 

 
var topFive = result.slice(0, 5); 
 
console.log(topFive);

<div id="main">This is a test to show that it is all about being between others. I am there until 8 pm event though it will be late. Because it is "cold" outside even though it is besides me.</div>