57 research outputs found
A Hybrid System for Subjectivity Analysis
No full textWe suggested different structured hybrid systems for the sentence-level subjectivity analysis based on three supervised machine learning algorithms, namely, Hidden Markov Model, Fuzzy Control System, and Adaptive Neuro-Fuzzy Inference System. The suggested feature extraction algorithm in our experiment computes a feature vector using statistical textual terms frequencies in a training dataset not having the use of any lexical knowledge except tokenization. Taking into consideration this fact, the above-mentioned methods may be employed in other languages as these methods do not utilize the morphological, syntactical, and lexical analysis in the classification problems
AZERNEWSV1: AZERBAIJANI NEWS CLASSIFICATION DATASET
No full text<div>
<div>
<div>
<p>Our dataset encompasses a comprehensive collection of Azerbaijani news texts from the Azertac (<a href="https://azertag.az/" rel="nofollow">https://azertag.az/</a>) State Agency, drawn from a variety of news articles. </p>
<p>Azertac, established on March 1, 1920, was recognized as a pioneering entity within the framework of international information agencies. It has played a pivotal role in the establishment and coordination of various associations, including the Association of National Information Agencies comprising nations affiliated with the Commonwealth of Independent States, the Association of News Agencies representing Turkish-speaking countries, and the Association of National News Agencies associated with countries participating in the Black Sea Economic Cooperation Organization. AZERTAC has engaged in collaborative endeavors with several renowned news agencies to foster global information exchange and cooperation. This extensive network of collaborations underscores Azertac's global reach and influence in international news dissemination.</p>
<p>The dataset comprises approximately three million rows, with each row representing a sentence extracted from diverse Azerbaijani news sources. These sentences cover a wide spectrum of subjects, including but not limited to politics, the economy, culture, sports, technology, and health. The Labeled dataset, which has been posted and publicly shared in the link, is organized to facilitate rigorous analysis and classification tasks, with essential metadata provided for each sentence.</p>
<p>The dataset is enriched with crucial metadata attributes that enhance its utility and applicability to various research tasks:</p>
<ul>
<li>News Category: Each sentence is linked to a specific news category, covering subjects such as politics, economy, culture, sports, technology, and health.</li>
<li> </li>
<li>News Subcategory: Further enhance granularity, each sentence is classified into a subcategory, enabling fine-tuned analysis and specialized classification tasks.</li>
<li> </li>
<li>News Index: A unique identifier for each news article maintains the dataset integrity and supports cross-referencing.</li>
<li> </li>
<li>News Sentence Order: Sequential order aids in preserving sentence context, which is essential for text generation and summarization.</li>
<li> </li>
<li>Link: Hyperlinks to original articles provide direct access for researchers to delve into the sentence context.</li>
<li> </li>
<li>Sentence: The core textual content, which varies in length and complexity, covers a spectrum of linguistic styles and themes.</li>
</ul>
<p> </p>
<p> </p>
</div>
</div>
</div>
<div>
<div>Instructions: </div>
<div>
<div>
<p>Dataset is presented in single csv file.</p>
<p>The dataset is enriched with crucial metadata attributes that enhance its utility and applicability to various research tasks:</p>
<ul>
<li>News Category: Each sentence is linked to a specific news category, covering subjects such as politics, economy, culture, sports, technology, and health.</li>
<li> </li>
<li>News Subcategory: Further enhance granularity, each sentence is classified into a subcategory, enabling fine-tuned analysis and specialized classification tasks.</li>
<li> </li>
<li>News Index: A unique identifier for each news article maintains the dataset integrity and supports cross-referencing.</li>
<li> </li>
<li>News Sentence Order: Sequential order aids in preserving sentence context, which is essential for text generation and summarization.</li>
<li> </li>
<li>Link: Hyperlinks to original articles provide direct access for researchers to delve into the sentence context.</li>
<li> </li>
<li>Sentence: The core textual content, which varies in length and complexity, covers a spectrum of linguistic styles and themes.</li>
</ul>
</div>
</div>
</div>
Evaluation of the Impact of the Tax Legislation Reforms on the Tax Potential by Fuzzy Inference Method
No full textAbstractIn the paper the Mamdani-Type Fuzzy inference method is applied for the expert evaluation of the impact of the tax legislation reforms on the tax potential. The model being investigated includes 4 inputs, 8 IF-THEN rules and a single-output. Triangle, trapezoid, Gaussian and Bell-shaped membership functions are used for the fuzzification of input data and output of the system is evaluated by Gaussian curve membership function. For the investigated year the laws made reforms in the Azerbaijan tax legislation are classified and evaluated on the base of fuzzy inference system
Sentiment Analysis of Azerbaijani twits Using Logistic Regression, Naive Bayes and SVM
No full text13th IEEE International Conference on Application of Information and Communication Technologies (AICT) -- OCT 23-25, 2019 -- Baku, AZERBAIJANIn the work, the roadmap of sentiment analysis of twits in Azerbaijani language has been developed. the principles of collecting, cleaning and annotating of twits for Azerbaijani language are described. Machine learning algorithms, such as Linear regression, Naive Bayes and SVM applied to detect sentiment polarity of text based on bag of word models. Our suggested approach for data processing and classification can be easily adapted and applied to other Turkish language. Achieved results from different machine learning algorithm have been compared and defined optimal parameters for the classification of twits.IEEE, ADA University, Azerbaijan Natl Acad Sci, Inst Informat Technol, Univ Malaysia Sabah, Pasha Ban
Scenario of Linguo – Cultural Essence of Verbs Expressing Behavior Peculiar to the Uzbeks
No full textThe author analyses lingua-cognitive and linguo-cultural essence of the verbs compiling the scenario of spiritual processes peculiar to the conduct of the Uzbeks. Here, the verbs compiling this scenario, based on systematic peculiarities in paradigmatic relations, go into syntagmatic relations, in expressing the very reality. The author also says that this condition creates instantaneous condition and this condition put them in order of a new system. In this order, the basis of verbs is stable lingua-cultural value. The author tries to prove that some verbs serve as direct unifiers of the events of a literary work
IBN SINO FALSAFIY QARASHLARINI O‘RGANILISH TARIXIDAN
No full textВ статье говорится о философских взглядах в творчестве Ибн Сины и истории их изучения. Автор Ибн Сина пытался осветить философскую суть своих произведений, написанных в области философии, природы, медицины и художественной литературы, а также музыки.The article talks about the philosophical views in the works of Ibn Sina and the history of their study. The author Ibn Sina tried to illuminate the philosophical essence of his works written in the fields of philosophy, nature, medicine and fiction, as well as music.Maqolada Ibn Sino ijodida falsafiy qarashlar va ularning o‘rganilish tarixi haqida so‘z borgan. Muallif Ibn Sino falsafa, tabiat, tibbiyot va badiiy adabiyotda, musiqa kabi boshqa fanlar sohasida yozgan asarlarini falsafiy mohiyatini yoritishga harakat qilgan
- …
