Yazar "Tokat, Sezai" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim
    Öğe
    Deep sentiment analysis: a case study on stemmed Turkish Twitter data
    (IEEE, 2021) Shehu, Harisu Abdullahi; Sharif, Md. Haidar; Sharif, Md. Haris Uddin; Datta, Ripon; Tokat, Sezai; Uyaver, Şahin; Kusetoğulları, Hüseyin; Ramadan, Rabie A.
    Sentiment analysis using stemmed Twitter data from various languages is an emerging research topic. In this paper, we address three data augmentation techniques namely Shift, Shuffle, and Hybrid to increase the size of the training data; and then we use three key types of deep learning (DL) models namely recurrent neural network (RNN), convolution neural network (CNN), and hierarchical attention network (HAN) to classify the stemmed Turkish Twitter data for sentiment analysis. The performance of these DL models has been compared with the existing traditional machine learning (TML) models. The performance of TML models has been affected negatively by the stemmed data, but the performance of DL models has been improved greatly with the utilization of the augmentation techniques. Based on the simulation, experimental, and statistical results analysis deeming identical datasets, it has been concluded that the TML models outperform the DL models with respect to both training-time (TTM) and runtime (RTM) complexities of the algorithms; but the DL models outperform the TML models with respect to the most important performance factors as well as the average performance rankings.
  • [ X ]
    Öğe
    Sentiment Analysis of Turkish Twitter Data
    (Amer Inst Physics, 2019) Shehu, Harisu Abdullahi; Tokat, Sezai; Sharif, Md. Haidar; Uyaver, Sahin
    In this paper, we present a mechanism to predict the sentiment on Turkish tweets by adopting two methods based on polarity lexicon (PL) and artificial intelligence (AI). The method of PL introduces a dictionary of words and matches the words to those in the harvested tweets. The tweets are then classified to be either positive, negative, or neutral based on the result found after matching them to the words in the dictionary. The method of AI uses support vector machine (SVM) and random forest (RF) classifiers to classify the tweets as either positive, negative or neutral. Experimental results show that SVM performs better on stemmed data by achieving an accuracy of 76%, whereas RF performs better on raw data with an accuracy of 88%. The performance of PL method increases continuously from 45% to 57% as data are being modified from a raw data to a stemmed data.
  • [ X ]
    Öğe
    Sentiment analysis of turkish twitter data using polarity lexicon and artificial intelligence
    (Springer Science and Business Media Deutschland GmbH, 2020) Shehu, Harisu Abdullahi; Haidar, Sharif; Uyaver, Şahin; Tokat, Sezai; Ramadan, Rabie A.
    Sentiment analysis is a process of computationally detecting and classifying opinions written in a piece of writer’s text. It determines the writer’s impression as achromatic or negative or positive. Sentiment analysis became unsophisticated due to the invention of Internet-based societal media. At present, usually people express their opinions by dint of Twitter. Henceforth, Twitter is a fascinating medium for researchers to perform data analysis. In this paper, we address a handful of methods to prognosticate the sentiment on Turkish tweets by taking up polarity lexicon as well as artificial intelligence. The polarity lexicon method uses a dictionary of words and accords with the words among the harvested tweets. The tweets are then grouped into either positive tweets or negative tweets or neutral tweets. The methods of artificial intelligence use either individually or combined classifiers e.g., support vector machine (SVM), random forest (RF), maximum entropy (ME), and decision tree (DT) for categorizing positive tweets, negative tweets, and neutral tweets. To analyze sentiment, a total of 13000 Turkish tweets are collected from Twitter with the help of Twitter’s application programming interface (API). Experimental results show that the mean performance of our proposed methods is greater than 72%. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020.