Lexicon-based emotion analysis in Turkish

Toçoğlu, Mansur Alp; Alpkoçak, Adil

doi:10.3906/elk-1807-41

Cited by 13 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lexicon-based sentiment analysis uses preconstructed emotional lexicons for determining the polarity of textual content (Turney, 2002). Each text is searched for revealing emotional terms given in the lexicon and then weights are assigned to each of those terms (Toçoğlu and Alpkocak, 2019). Lexicon-based classification does not need to be labeled data, but it is difficult to create a unique lexically based dictionary to be used for different contexts.…”

Section: Literature Reviewmentioning

confidence: 99%

A supervised data mining approach for predicting comment card ratings

Tanrısevdi

Özturk

Öztürk

2022

IJCHM

View full text Add to dashboard Cite

Purpose The purpose of this study is to develop a review rating prediction method based on a supervised text mining approach for unrated customer reviews. Design/methodology/approach Using 2,851 hotel comment card (HCC) reviews, this paper manually labeled positive and negative comments with seven aspects (dining, cleanliness, service, entertainment, price, public, room) that emerged from the content of said reviews. After text preprocessing (tokenization, eliminating punctuation, stemming, etc.), two classifier models were created for predicting the reviews’ sentiments and aspects. Thus, an aggregate rating scale was generated using these two classifier models to determine overall rating values. Findings A new algorithm, Comment Rate (CRate), based on supervised learning, is proposed. The results are compared with another review-rating algorithm called location based social matrix factorization (LBSMF) to check the consistency of the proposed algorithm. It is seen that the proposed algorithm can predict the sentiments better than LBSMF. The performance evaluation is performed on a real data set, and the results indicate that the CRate algorithm truly predicts the overall rating with ratio 80.27%. In addition, the CRate algorithm can generate an overall rating prediction scale for hotel management to automatically analyze customer reviews and understand the sentiment thereof. Research limitations/implications The review data were only collected from a resort hotel during a limited period. Therefore, this paper cannot explore the effect of independent variables on the dependent variable in context of larger period. Practical implications This paper provides a novel overall rating prediction technique allowing hotel management to improve their operations. With this feature, hotel management can evaluate guest feedback through HCCs more effectively and quickly. In this way, the hotel management will be able to identify those service areas that need to be developed faster and more effectively. In addition, this review rating prediction approach can be applied to customer reviews posted via online platforms for detecting review and rating reliability. Originality/value Manually analyzing textual information is time-consuming and can lead to measurement errors. Therefore, the primary contribution of this study is that although comment cards do not have rating values, the proposed CRate algorithm can predict the overall rating and understand the sentiment of the reviews in question.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A supervised data mining approach for predicting comment card ratings

Tanrısevdi

Özturk

Öztürk

2022

IJCHM

View full text Add to dashboard Cite

show abstract

“…To annotate tweets, we have intensively used TEL, which consists of 7,235 keywords, in total, for six emotion categories of fear, happy, disgust, anger, sadness, surprise [36]. Table 1 shows sample keywords selected from TEL for each emotion category, where English translations are presented in italic.…”

Section: B Curation Of Datasetmentioning

confidence: 99%

“…For annotation, we performed a lexicon-based automatic annotation process using TEL [36], which includes keywords lemmatized by TurkLemma [38]. Then, we annotated each tweet with a category name of a TEL keyword contains in that tweet.…”

Section: B Curation Of Datasetmentioning

confidence: 99%

Emotion Analysis From Turkish Tweets Using Deep Neural Networks

2019

Self Cite

View full text Add to dashboard Cite

Text data analysis of social media is becoming more and more important since it includes the most recent information on what people think about. Likewise, emotion is one of the most valuable parts of human communication, emotion analysis is a type of information extraction process which identifies the emotional states of a given text. In this study, we investigated the performance of deep neural networks on emotion analysis from Turkish tweets. For this, we examined three different deep learning architectures including artificial neural network (ANN), convolutional neural network (CNN) and recurrent neural network (RNN) with long short-term memory (LSTM). Besides, we curated a dataset of Turkish tweets and annotated each tweet automatically for six emotion categories using a lexicon-based approach. For the evaluation, we conducted a set of experiments for each architecture. The results showed that the lexiconbased automatic annotation of tweets is valid. Secondly, ANN produced the worst result as expected, and CNN resulted in the highest score of 0.74 in terms of accuracy measure. Experiments also showed that our proposed approach for emotion analysis of tweets in Turkish performs better than state-of-the-art in this topic.

show abstract

“…In the experiments performed on TREMO, the highest performance was achieved with the SVM with an 86% general accuracy. In the continuation study [32], an emotion lexicon was produced using TREMO, and lexicon-based emotion analysis was performed. The lexicon-based approach proposed in the study showed competitive performance against the TML methods with an accuracy of 91%.…”

Section: Introductionmentioning

confidence: 99%

A study of Turkish emotion classification with pretrained language models

Uçan

Dörterler

Sezer

2021

Journal of Information Science

View full text Add to dashboard Cite

Emotion classification is a research field that aims to detect the emotions in a text using machine learning methods. In traditional machine learning (TML) methods, feature engineering processes cause the loss of some meaningful information, and classification performance is negatively affected. In addition, the success of modelling using deep learning (DL) approaches depends on the sample size. More samples are needed for Turkish due to the unique characteristics of the language. However, emotion classification data sets in Turkish are quite limited. In this study, the pretrained language model approach was used to create a stronger emotion classification model for Turkish. Well-known pretrained language models were fine-tuned for this purpose. The performances of these fine-tuned models for Turkish emotion classification were comprehensively compared with the performances of TML and DL methods in experimental studies. The proposed approach provides state-of-the-art performance for Turkish emotion classification.

show abstract

Lexicon-based emotion analysis in Turkish

Cited by 13 publications

References 21 publications

A supervised data mining approach for predicting comment card ratings

A supervised data mining approach for predicting comment card ratings

Emotion Analysis From Turkish Tweets Using Deep Neural Networks

A study of Turkish emotion classification with pretrained language models

Contact Info

Product

Resources

About