Make lexicon to be easily updated on the fly

Author: davmixcool

README.md

@@ -33,7 +33,7 @@ Run the following to include this via Composer
 composer require davmixcool/php-sentiment-analyzer
 ```
 
-### Usage
+### Simple Usage
 
 ```php
 
@@ -52,17 +52,87 @@ print_r($output_text_with_emoji);
 
 ```
 
-### Outputs
+### Simple Outputs
 
 ```
 David is smart, handsome, and funny. ---------------- ['neg'=> 0.0, 'neu'=> 0.337, 'pos'=> 0.663, 'compound'=> 0.7096]
 
 😁 ------------------- ['neg' => 0, 'neu' => 0.5, 'pos' => 0.5, 'compound' => 0.4588]
 
-Aproko doctor made me 🤣 ------------- ['neg' => 0, 'neu' => 1, 'pos' => 0, 'compound' => 0]
+Aproko doctor made me 🤣 ------------- ['neg' => 0, 'neu' => 0.714, 'pos' =>  0.286, 'compound' => 0.4939]
 
 ```
 
+
+
+### Advance Usage
+
+You can now dynamically update the VADER (Valence) lexicon on the fly for words that are not in the dictionary. See Example below:
+
+
+```php
+
+
+Use Sentiment\Analyzer;
+
+$sentiment = new Sentiment\Analyzer();
+
+$strings = [
+	'Weather today is rubbish',
+	'This cake looks amazing',
+	'His skills are mediocre',
+	'He is very talented',
+	'She is seemingly very agressive',
+	'Marie was enthusiastic about the upcoming trip. Her brother was also passionate about her leaving - he would finally have the house for himself.',
+	'To be or not to be?',
+];
+
+//new words not in the dictionary
+$newWords = [
+	'rubbish'=> '-1.5',
+	'mediocre' => '-1.0',
+	'agressive' => '-0.5'
+];
+
+//Dynamically update the dictionary with the new words
+$sentiment->updateLexicon($newWords);
+
+//Print results
+foreach ($strings as $string) {
+	// calculations:
+	$scores = $sentiment->getSentiment($string);
+	// output:
+	echo "String: $string\n";
+	print_r(json_encode($scores));
+	echo "<br>";
+}
+
+
+```
+
+
+### Advance Outputs
+
+
+```
+
+Weather today is rubbish  ------------- {"neg":0.455,"neu":0.545,"pos":0,"compound":-0.3612} 
+
+This cake looks amazing  ------------- {"neg":0,"neu":0.441,"pos":0.559,"compound":0.5859}
+
+His skills are mediocre  ------------- {"neg":0.4,"neu":0.6,"pos":0,"compound":-0.25}
+
+He is very talented  ------------- {"neg":0,"neu":0.457,"pos":0.543,"compound":0.552}
+
+She is seemingly very agressive  ------------- {"neg":0.338,"neu":0.662,"pos":0,"compound":-0.2598}
+
+Marie was enthusiastic about the upcoming trip. Her brother was also passionate about her leaving - he would finally have the house for himself.  ------------- {"neg":0,"neu":0.761,"pos":0.239,"compound":0.765}
+
+String: To be or not to be?  ------------- {"neg":0,"neu":1,"pos":0,"compound":0}
+
+```
+
+
 ### License
 
 This package is licensed under the [MIT license](https://github.com/davmixcool/php-sentiment-analyzer/blob/master/LICENSE).

src/Analyzer.php

@@ -83,6 +83,15 @@ public function make_emoji_dict() {
         return $emoji_dict;
     }
 
+    public function updateLexicon($arr)
+    {
+        if(!is_array($arr)) return [];
+        $lexicon = [];
+        foreach ($arr as $word => $valence) {
+            $this->lexicon[strtolower($word)] = is_numeric($valence)? $valence : 0;
+        }
+    }
+
     private function IsKindOf($firstWord, $secondWord)
     {
         return "kind" === strtolower($firstWord) && "of" === strtolower($secondWord);
@@ -183,19 +192,20 @@ public function getSentiment($text)
         $sentiments = [];
         $words_and_emoticons = $this->current_sentitext->words_and_emoticons;
 
-        for ($i=0; $i<count($words_and_emoticons)-1; $i++) {
+        for ($i=0; $i<=count($words_and_emoticons)-1; $i++) {
             $valence = 0.0;
             $wordBeingTested = $words_and_emoticons[$i];
 
             //If this is a booster word add a 0 valances then go to next word as it does not express sentiment directly
            /* if ($this->IsBoosterWord($wordBeingTested)){
                 echo "\t\tThe word is a booster word: setting sentiment to 0.0\n";
             }*/
-
+ //var_dump($i);
             //If the word is not in the Lexicon then it does not express sentiment. So just ignore it.
             if ($this->IsInLexicon($wordBeingTested)) {
+
                 //Special case because kind is in the lexicon so the modifier kind of needs to be skipped
-                if ("kind" !=$words_and_emoticons[$i] && "of" != $words_and_emoticons[$i+1]) {
+                if ("kind" !=$words_and_emoticons[$i] && "of" != $words_and_emoticons[$i]) {
                     $valence = $this->getValenceFromLexicon($wordBeingTested);
 
                     $wordInContext = $this->getWordInContext($words_and_emoticons, $i);

src/Config/Config.php

@@ -40,7 +40,7 @@ class Config
      "fricking"=> self::B_INCR, "frickin"=> self::B_INCR, "frigging"=> self::B_INCR, "friggin"=> self::B_INCR, "fully"=> self::B_INCR, "fucking"=> self::B_INCR,
      "greatly"=> self::B_INCR, "hella"=> self::B_INCR, "highly"=> self::B_INCR, "hugely"=> self::B_INCR, "incredibly"=> self::B_INCR,
      "intensely"=> self::B_INCR, "majorly"=> self::B_INCR, "more"=> self::B_INCR, "most"=> self::B_INCR, "particularly"=> self::B_INCR,
-     "purely"=> self::B_INCR, "quite"=> self::B_INCR, "really"=> self::B_INCR, "remarkably"=> self::B_INCR,
+     "purely"=> self::B_INCR, "quite"=> self::B_INCR, "seemingly" => self::B_INCR, "really"=> self::B_INCR, "remarkably"=> self::B_INCR,
      "so"=> self::B_INCR, "substantially"=> self::B_INCR,
      "thoroughly"=> self::B_INCR, "totally"=> self::B_INCR, "tremendous"=> self::B_INCR, "tremendously"=> self::B_INCR,
      "uber"=> self::B_INCR, "unbelievably"=> self::B_INCR, "unusually"=> self::B_INCR, "utterly"=> self::B_INCR,