Whereas, in the case of Convolutional Neural Network the experiment result shows that the accuracy of 89% is achieved. According to the experiment, the result shows that for MNB approach accuracy of 90.7%, 71.1%, 54.6%, 92.78%, 92.44%, and 75% for unigram, bigram, trigram, unigram-bigram, unigram-trigram and bigram-trigram respectively. For classifiers, we used 80% training and 20% testing rule. We conducted our experiment on the selected classifiers.
We used the Keras deep learning python library to implement both deep learning algorithms. In the case of Long Short Term Memory and Convolutional Neural Network, we used word embedding as a feature. Using the Scikit-learn feature extraction python library Term FrequencyInverse Document Frequency Vectorizer and n-gram range we build the feature extraction method for Naïve Bayes Approach. Preprocessing, normalization, tokenization, stop word removal, stemming of the sentence are performed. After collecting the data, manual annotation is undertaken.
To this end, a total of 1452 comments collected from the official site of the Facebook page of Oromo Democratic Party/ODP for the study. Therefore, in this study, we focused on investigating Convolutional Neural Network, Long Short Term Memory and Multinomial Naïve Bayes machine learning approaches for the development of sentiment analysis of Afaan Oromoo social media content such as Facebook posts comments. To the best of the researcher’s knowledge, there is no machine learning approach done for Afaan Oromoo Sentiment analysis to identify the opinion of the people on social media content. In general, sentiment analysis is the process of automatically identifying and categorizing opinions in order to determine whether the writer's attitude towards a particular entity is positive or negative. Therefore, sentiment analysis has increasingly become a major area of research interest in the field of Natural Language Processing and Test Mining. Nevertheless, many organizations and individuals are highly interested to know what other peoples are thinking or feeling about their services and products. The major problem with sentiment analysis of social media posts is that it is extremely vast, fragmented, unorganized and unstructured. This study focuses on sentiment analysis of social media content because automatically identifying and classifying opinions from social media posts can provide significant economic values and social benefits. The rapid development and popularity of social media and social networks provide people with unprecedented opportunities to express and share their thoughts, views, opinions and feelings about almost anything through their personal webpages and blogs or using social network sites like Facebook, Twitter, and Blogger.
0 kommentar(er)
