TREMO: A dataset for emotion analysis in Turkish

Toçoğlu, Mansur Alp; Alpkoçak, Adil

doi:10.1177/0165551518761014

Cited by 24 publications

(20 citation statements)

References 15 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, the anger emotion category obtained the lowest accuracy value for SVM, RF, and lexiconbased approach. This is because anger emotion category is likely to be confused with fear and sadness emotion categories [35]. Table 12 shows the overall evaluation results in terms of accuracy, precision, recall, and f-measure for each classification method.…”

Section: Experiments and Discussionmentioning

confidence: 99%

“…In this article, we proposed a Turkish emotion lexicon (TEL) 1 that can be used in emotion analysis in Turkish text for six emotion categories. To the best of our knowledge, it is the first Turkish lexicon which is generated from an original Turkish dataset, TREMO, in the literature [35]. To create the lexicon, we examined the effects of a lemmatizer and a stemmer, two term-weighting schemes, four different lexicon enrichment methods, and a term selection process for lexicon-based emotion analysis, respectively.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Lexicon-based emotion analysis in Turkish

Toçoğlu¹,

Alpkoçak²

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

In this paper, we proposed a lexicon for emotion analysis in Turkish for six emotional categories happiness, fear, anger, sadness, disgust, and surprise. Besides, we also investigated the effects of a lemmatizer and a stemmer, two term-weighting schemes, four lexicon enrichment methods, and a term selection approach for lexicon construction. To do this, we generated Turkish emotion lexicon based on a dataset, TREMO, containing 25,989 documents. We then preprocessed the documents to obtain dictionary and stem forms of each term using a lemmatizer and a stemmer. Afterwards, we proposed two different weighting schemes where term frequency, term-class frequency and mutual information (MI) values for six emotion categories are taken into consideration. We then enriched the lexicon by using bigram and concept hierarchy methods, and performed term selection for efficiency issues. Then, we compared the performance of lexicon-based approach with machine learning based approach by using our proposed lexicon. The experiments showed that the use of the proposed lexicon efficiently produces comparable results in emotion analysis in Turkish text.

show abstract

Section: Experiments and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Lexicon-based emotion analysis in Turkish

Toçoğlu¹,

Alpkoçak²

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

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%

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

Shehu

Sharif

et al. 2021

IEEE Access

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

“…As a second method is supervised LSTM [33]. As the training data, the results accepted by unanimous or majority vote from 34.397 classified comments in the TREMO [34] data set were used. The labels in this training data have been converted as positive, negative and neutral.…”

Section: Figure 8 Cumulative Data Graph Of Death and Interpretation By Daysmentioning

confidence: 99%

Finding the Relationship Between News and Social Media Users’ Emotions in the COVID-19 Process

Müngen

Aygün

Kaya

2020

Sakarya University Journal of Computer and Information Sciences

View full text Add to dashboard Cite

Nowadays, social media and online sharing sites are frequently used to share thoughts about daily events. Thanks to the posts made by internet users on these platforms, first, quite big data is generated to interpret the agenda. More than 10,000 comments of more than 5000 users made about COVID-19 from online websites between 15 March and 15 May were collected in this study. Then, emotional analysis on these comments was carried out with BERT, GRU, LSTM and TF-IDF methods. The changes in the amount of user comments and the emotions reflected by the comments have been associated with the actual events of these dates. It has been determined which types of events affect users more. In addition, the emotional response changes of the users to the official COVID-19 statistics were measured and the peak points of the emotional changes were determined. Finally, the emotion classification methods applied were evaluated by user questionnaires and their successes were determined according to F-Measure.

show abstract

TREMO: A dataset for emotion analysis in Turkish

Cited by 24 publications

References 15 publications

Lexicon-based emotion analysis in Turkish

Lexicon-based emotion analysis in Turkish

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

Finding the Relationship Between News and Social Media Users’ Emotions in the COVID-19 Process

Contact Info

Product

Resources

About