Nowadays, social media is used by many people to express their opinions about a variety of topics. Opinion Mining or Sentiment Analysis techniques extract opinions from user generated contents. Over the years, a multitude of Sentiment Analysis studies has been done about the English language with deficiencies of research in all other languages. Unfortunately, Arabic is one of the languages that seems to lack substantial research, despite the rapid growth of its use on social media outlets. Furthermore, specific Arabic dialects should be studied, not just Modern Standard Arabic. In this paper, we experiment sentiments analysis of Iraqi Arabic dialect using word embedding. First, we made a large corpus from previous works to learn word representations. Second, we generated word embedding model by training corpus using Doc2Vec representations based on Paragraph and Distributed Memory Model of Paragraph Vectors (DM-PV) architecture. Lastly, the represented feature used for training four binary classifiers (Logistic Regression, Decision Tree, Support Vector Machine and Naive Bayes) to detect sentiment. We also experimented different values of parameters (window size, dimension and negative samples). In the light of the experiments, it can be concluded that our approach achieves a better performance for Logistic Regression and Support Vector Machine than the other classifiers.
Bu makaleye şu şekilde atıfta bulunabilirsiniz(To cite to this article): Alnawas A. and Arıcı N., "The corpus based approach to sentiment analysis in modern standard Arabic and Arabic dialects: a literature review", Politeknik Dergisi, 21(2): 461-470, (2018).Erişim linki (To link to this article): http://dergipark.gov.tr/politeknik/archive DOI: 10.2339/politeknik.403975 Politeknik Dergisi, 2018;21(2):461-470 Journal of Polytechnic, 2018;21(2) With the increase in applications on the Internet and social networks, Sentiment Analysis has taken a considerable place in the field of text mining research and has since been used to explore the opinions of users about various products or topics discussed over the Internet. When the literature on Sentiment Analysis is examined, it is seen that the natural language of the Internet information sources that form the basis of the analysis is mostly English. Developments in the fields of Natural Language Processing and Computational Linguistics have contributed positively to Sentiment Analysis studies made from natural languages other than English. The purpose of this study is to examine the literature of Sentiment Analysis conducted in Arabic internet information sources. The literature review includes studies based on the corpus approach, which is made up of Arabic Internet information sources. Studies are being carried out on the works which constitute their own corpora for both Modern Standard Arabic and Arabic dialects and on which sentiment analysis is performed.
E-Learning has become an essential teaching approach during the COVID-19 pandemic. All over the world, various internet-based learning management systems (Google classroom, Moodle, etc.) were adopted to convey knowledge and enhance learning outcomes. However, measuring learning outcomes and knowledge acquisition in E-Learning environment is a controversial issue. To this end, this paper aims to predict learning outcomes using data mining techniques. Student data are collected and analyzed to construct the prediction model. The collected data covered students from various undergraduate studies. Cross-Industry Standard Process for Data Mining is used as a research model. The obtained result shows the significant of some attributes in predicting learning outcomes. Four correlation-based attributes selection schemas are applied. The selected attributes are examined using four data mining algorithms: random forest, k-nearest neighbors, Decision Tree, and neural network. The overall performance of the constructed mining models is evaluated using various performance measures: Accuracy, Precision, Recall and F1-score are calculated. Overall, an 86% accuracy is secured.
Rainfall is considered a main to provide water in rivers along with Iraqi territory. The unpredictable amount of rainfall due to climate change can cause either overflow or dry in the rivers. Although, there are a lot of electronic devices that have harnessed the prediction of precipitation using weather conditions such as humidity pressure, and temperature. Regrettably, these classical methods cannot work efficiently, so exploiting machine learning techniques can predict accurate outcomes. Therefore, predictions of databased models using deep learning algorithms are promising for these purposes. This empirical study seeks to build a precipitation prediction model using a deep learning mechanism through utilizing historical weather data. Deep learning outperformed other classifiers based on the findings collected. The current study's experiment yielded accurate findings of up to 91.59% when testing the model with actual weather data within the specified period.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.