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.
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 |
You can also see Python, Java, C, C++, Swift, Js, Php, or C# repository.
To check if you have a compatible version of Python installed, use the following command:
python -V
You can find the latest version of Python here.
Install the latest version of Git.
pip3 install NlpToolkit-SentiNet-Cy
In order to work on code, create a fork from GitHub page. Use Git for cloning the code to your local or below line for Ubuntu:
git clone <your-fork-git-link>
A directory called SentiNet will be created. Or you can use below link for exploring the code:
git clone https://github.com/starlangsoftware/TurkishSentiNet-Cy.git
Steps for opening the cloned project:
- Start IDE
- Select File | Open from main menu
- Choose
TurkishSentiNet-CYfile - Select open as project option
- Couple of seconds, dependencies will be downloaded.
Duygu sözlüğünü yüklemek için
a = SentiNet()
Belirli bir alana ait duygu sözlüğünü yüklemek için
SentiNet(fileName: str)
a = SentiNet("dosya.txt")
Belirli bir synsete ait duygu synsetini elde etmek için
getSentiSynSet(self, _id: str) -> SentiSynSet
Bir SentiSynset elimizdeyken onun pozitif skorunu
getPositiveScore(self) -> float
negatif skorunu
getNegativeScore(self) -> float
polaritysini
getPolarity(self) -> PolarityType
@inproceedings{ozcelik21,
title={{H}is{N}et: {A} {P}olarity {L}exicon based on {W}ord{N}et for {E}motion {A}nalysis},
year={2021},
author={M. Ozcelik and B. N. Arican and O. Bakay and E. Sarmis and N. B. Bayazit and O. Ergelen and O. T. Y{\i}ld{\i}z},
booktitle={Proceedings of GWC 2021}
}
- Do not forget to set package list. All subfolders should be added to the package list.
packages=['Classification', 'Classification.Model', 'Classification.Model.DecisionTree',
'Classification.Model.Ensemble', 'Classification.Model.NeuralNetwork',
'Classification.Model.NonParametric', 'Classification.Model.Parametric',
'Classification.Filter', 'Classification.DataSet', 'Classification.Instance', 'Classification.Attribute',
'Classification.Parameter', 'Classification.Experiment',
'Classification.Performance', 'Classification.InstanceList', 'Classification.DistanceMetric',
'Classification.StatisticalTest', 'Classification.FeatureSelection'],
- Package name should be lowercase and only may include _ character.
name='nlptoolkit_math',
- Package data should be defined and must ibclude pyx, pxd, c and py files.
package_data={'NGram': ['*.pxd', '*.pyx', '*.c', '*.py']},
- Setup should include ext_modules with compiler directives.
ext_modules=cythonize(["NGram/*.pyx"],
compiler_directives={'language_level': "3"}),
- Define the class variables and class methods in the pxd file.
cdef class DiscreteDistribution(dict):
cdef float __sum
cpdef addItem(self, str item)
cpdef removeItem(self, str item)
cpdef addDistribution(self, DiscreteDistribution distribution)
- For default values in class method declarations, use *.
cpdef list constructIdiomLiterals(self, FsmMorphologicalAnalyzer fsm, MorphologicalParse morphologicalParse1,
MetamorphicParse metaParse1, MorphologicalParse morphologicalParse2,
MetamorphicParse metaParse2, MorphologicalParse morphologicalParse3 = *,
MetamorphicParse metaParse3 = *)
- Define the class name as cdef, class methods as cpdef, and __init__ as def.
cdef class DiscreteDistribution(dict):
def __init__(self, **kwargs):
"""
A constructor of DiscreteDistribution class which calls its super class.
"""
super().__init__(**kwargs)
self.__sum = 0.0
cpdef addItem(self, str item):
- Do not forget to comment each function.
cpdef addItem(self, str item):
"""
The addItem method takes a String item as an input and if this map contains a mapping for the item it puts the
item with given value + 1, else it puts item with value of 1.
PARAMETERS
----------
item : string
String input.
"""
- Function names should follow caml case.
cpdef addItem(self, str item):
- Local variables should follow snake case.
det = 1.0
copy_of_matrix = copy.deepcopy(self)
- Variable types should be defined for function parameters, class variables.
cpdef double getValue(self, int rowNo, int colNo):
- Local variables should be defined with types.
cpdef sortDefinitions(self):
cdef int i, j
cdef str tmp
- For abstract methods, use ABC package and declare them with @abstractmethod.
@abstractmethod
def train(self, train_set: list[Tensor]):
pass
- For private methods, use __ as prefix in their names.
cpdef list __linearRegressionOnCountsOfCounts(self, list countsOfCounts)
- For private class variables, use __ as prefix in their names.
cdef class NGram:
cdef int __N
cdef double __lambda1, __lambda2
cdef bint __interpolated
cdef set __vocabulary
cdef list __probability_of_unseen
- Write __repr__ class methods as toString methods
- Write getter and setter class methods.
cpdef int getN(self)
cpdef setN(self, int N)
- If there are multiple constructors for a class, define them as constructor1, constructor2, ..., then from the original constructor call these methods.
cdef class NGram:
cpdef constructor1(self, int N, list corpus):
cpdef constructor2(self, str fileName):
def __init__(self,
NorFileName,
corpus=None):
if isinstance(NorFileName, int):
self.constructor1(NorFileName, corpus)
else:
self.constructor2(NorFileName)
- Extend test classes from unittest and use separate unit test methods.
class NGramTest(unittest.TestCase):
def test_GetCountSimple(self):
- For undefined types use object as type in the type declarations.
cdef class WordNet:
cdef object __syn_set_list
cdef object __literal_list
- For boolean types use bint as type in the type declarations.
cdef bint is_done
- Enumerated types should be used when necessary as enum classes, and should be declared in py files.
class AttributeType(Enum):
"""
Continuous Attribute
"""
CONTINUOUS = auto()
"""
- Resource files should be taken from pkg_recources package.
fileName = pkg_resources.resource_filename(__name__, 'data/turkish_wordnet.xml')