README

Polarity Lexicons

Exploiting a dictionary-based method necessitates the construction of a specific polarity dictionary in the same language as the data-to-be-analyzed. The reason behind this necessity stems from the improbability of creating a universal polarity dictionary due to both grammatical and cultural asymmetries between languages. For instance, a certain historical event can have positive connotations in one culture and negative connotations in another culture. Thus, it is an essential step to create a language specific polarity dictionary.

The first examples of polarity dictionary work could be found in English. SentiWordNet 1.0, the very first study on English polarity dictionaries, was presented by Esuli and Sebastiani (2006). Considerable research has been conducted to improve these resources with the aim of making them more precise. For example, the polarities of the objective words in SentiWordNet have been reassessed by Hung and Lini (2010). SenticNet (Cambria et al., 2014), another well-known dictionary in English, is created by rescoring words based on five different criteria, which are happiness, attention, sensitivity, ability and general polarity. Thus, it is evident that SenticNet is a polarity dictionary that provides a more extensive emotional evaluation than SentiWordNet.

There are polar dictionaries created in major languages other than English. However, these dictionaries were found to be insufficient in terms of the number of words. Brooke et al. (2009) aimed to translate English polarity sources to Spanish. At first, the methods established independent from the target language were found adequate, yet in the long term it was noticed that these methods were costly and inaccurate. Employing language-dependent resources to improve this system was deemed more feasible. Remus et al. (2010) have created a German sensitivity dictionary named SentiWortschatz for the German language. For the purpose of creating a feeling dictionary, over 3500 German words were assigned positive and nega- tive values in the range of [-1, 1], using PosTags. Abdaoui et al. (2017) have created the FEEL: a French Expanded Emotion Lexicon polarity dictionary for French. Moreno-Sandoval et al. (2017) have created the Combined Spanish Lexicon polarity dictionary for Spanish.

Turkish Polarity Lexicon HisNet

In this study, we present a polarity dictionary to provide an extensive polarity dictionary for Turkish that dictionary-based sentiment analysis studies have been longing for. Our primary objective is to provide a more refined and extensive polarity dictionary than the previous SentiTurkNet. In doing so, we have resorted to a different network from the referenced study. We have identified approximately 76,825 synsets from Kenet, which then were manually labeled as positive, negative or neutral by three native speakers of Turkish. The first labelling process resulted in 3,100 positive, 10,191 negative and 63,534 neutral data, during which decisions were based on the meaning and connotation of each word.

Subsequently, a second labeling was further made on positive and negative words as strong or weak based on their degree of positivity or negativity. For instance, the word mükemmel (excellent) in Turkish has been marked three times. Thus, three different views were obtained for the value of this word. While selecting the appropriate label, the compatibility of the labels selected by the three labelers was also evaluated. To put it differently, if a positive word receives strong label from all three annotators, it is regarded as strong positive. If it receives two strong and one weak label, it is considered as very positive. If it is la- belled as strong once and as weak twice, it means it is just positive. Finally, if it receives weak label from all three annotators, it is considered as weak positive. The same is also true for the words labelled as negative.

Polarity Level	# of Synsets
Strongly positive	1,038
Very positive	451
Positive	456
Weakly positive	1,234
Objective	63,534
Strongly negative	4,430
Very negative	1,465
Negative	1,238
Weakly negative	3,360

Simple Web Interface For Sentiment Lexicon

Link 1 Link 2

Video Lectures

For Contibutors

composer.json file

autoload is important when this package will be imported.

  "autoload": {
    "psr-4": {
      "olcaytaner\\WordNet\\": "src/"
    }
  },

Dependencies should be maximum (not only direct but also indirect references should also be given), everything directly in the code should be given here.

  "require-dev": {
    "phpunit/phpunit": "11.4.0",
    "olcaytaner/dictionary": "1.0.0",
    "olcaytaner/xmlparser": "1.0.1",
    "olcaytaner/morphologicalanalysis": "1.0.0"
  }

Data files

Add data files to the project folder. Subprojects should include all data files of the parent projects.

Php files

Do not forget to comment each function.

    /**
     * Returns true if specified semantic relation type presents in the relations list.
     *
     * @param SemanticRelationType $relationType element whose presence in the list is to be tested
     * @return bool true if specified semantic relation type presents in the relations list
     */
    public function containsRelationType(SemanticRelationType $relationType): bool{
        foreach ($this->relations as $relation){
            if ($relation instanceof SematicRelation && $relation->getRelationType() == $relationType){
                return true;
            }
        }
        return false;
    }

Function names should follow caml case.

    public function getRelation(int $index): Relation{

Write getter and setter methods.

    public function getOrigin(): ?string
    public function setName(string $name): void

Use standard javascript test style by extending the TestCase class. Use setup when necessary.

class WordNetTest extends TestCase
{
    private WordNet $turkish;

    protected function setUp(): void
    {
        ini_set('memory_limit', '450M');
        $this->turkish = new WordNet();
    }

    public function testSize()
    {
        $this->assertEquals(78327, $this->turkish->size());
    }

Enumerated types should be declared with enum.

enum CategoryType
{
    case MATHEMATICS;
    case SPORT;
    case MUSIC;
    case SLANG;
    case BOTANIC;

If there are multiple constructors for a class, define them as constructor1, constructor2, ..., then from the original constructor call these methods.

    public function constructor1(string $path, string $fileName): void
    public function constructor2(string $path, string $extension, int $index): void
    public function __construct(string $path, string $extension, ?int $index = null)

Use __toString method if necessary to create strings from objects.

    public function __toString(): string

Use xmlparser package for parsing xml files.

  $doc = new XmlDocument("../test.xml");
  $doc->parse();
  $root = $doc->getFirstChild();
  $firstChild = $root->getFirstChild();

olcaytaner / sentinet

Maintainers

Package info

Statistics

Security