Sentiment Analysis of Turkish Twitter Data Using Polarity Lexicon and Artificial Intelligence

Shehu, Harisu Abdullahi; Sharif, Haidar; Uyaver, Şahin; Tokat, Sezai; Ramadan, Rabie A.

doi:10.1007/978-3-030-60036-5_8

Cited by 4 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several research to analyze sentiment from Turkish texts have been carried out specifically on stemmed data [54], [62], [63], [66].…”

Section: B Rating the Stemmed Turkish Datamentioning

confidence: 99%

“…In our previous study [54], [62], we analyzed the sentiment of Turkish Twitter data on different datasets. We harvested data from Twitter and applied pre-processing operations (e.g., removal of punctuations and special characters to clean the data).…”

Section: B Rating the Stemmed Turkish Datamentioning

confidence: 99%

“…The Turkic language [51] as one of the world's fundamental languages are a language family of at least 35 documented languages [52]- [54], spoken by the Turkic peoples of Eurasia from Southern Europe, Eastern Europe, the Caucasus, Central Asia, Western Asia, North Asia, and East Asia [51]. The total number of the Turkic language speakers is over 200 million [55].…”

Section: Introductionmentioning

confidence: 99%

“…There are many text-based studies found in the literature on sentiment or opinion analysis in English language [29]. However, only a handful number of studies were found to be in Turkish [54], [58]- [62]. This is due to its inherent complexity.…”

Section: Introductionmentioning

confidence: 99%

“…We know from our previous work [54], [61], [62], that while the produced words after stemming helps improve the accuracy of the method using polarity lexicon, the achieved accuracy is relatively lower [54] using the traditional machine learning (TML) algorithms such as Naive Bayes (NB), Maximum Entropy (MAXE), Decision Tree (DECT), Random Forests (RANF), and Support Vector Machines (SVMs). Anecdotally, this is because by chopping the end of the tweets, the stemming reduces the amount of information gained from these tweets.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

Shehu

Sharif

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Several research to analyze sentiment from Turkish texts have been carried out specifically on stemmed data [54], [62], [63], [66].…”

Section: B Rating the Stemmed Turkish Datamentioning

confidence: 99%

Section: B Rating the Stemmed Turkish Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%