SmartSenti: A Twitter-Based Sentiment Analysis System for the Smart Tourism in Turkey

Salur, Mehmet Umut; Aydın, İlhan; Alghrsi, Shahed Alali

doi:10.1109/idap.2019.8875922

Cited by 14 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Data preprocessing has positive contributions to the processing of texts with both statistical methods and machine learning methods [32]- [34]. In line with the purpose of working with data preprocessing, datasets are reduced to normal form by purifying them of noisy content.…”

Section: Preprocessing Of Textsmentioning

confidence: 99%

An ensemble approach for aspect term extraction in Turkish texts

Salur¹,

Aydın²,

JAMOUS³

2022

Pamukkale J Eng Sci

View full text Add to dashboard Cite

Today, as a result of the inadequacies of the standard sentiment analysis, aspect-based sentiment analysis (ABSA) studies have great attracting interest. ABSA reveals detailed sentiment and opinion about every term/attribute in a text. The most important sub-stage of the ABSA method is the process of extracting the aspect terms from a text. This process becomes more difficult in texts with agglutinative language structures such as Turkish. In this study, we proposed an ensemble approach that uses statistical (TF-IDF), topic modeling (LDA and NMF), and rule-based methods together to extract aspect terms from Turkish user comments. The proposed method strategically combines the candidate aspect term obtained by different methods and determines the final aspect term lists. The proposed method has been tested on the SemEval-2016 ABSA benchmarking dataset, which consists of Turkish restaurant reviews. The experimental results of the proposed method were compared with previous studies on the same dataset.Günümüzde standart duygu analizinin yetersiz kalması sonucunda, hedef tabanlı duygu analizi (HTDA) çalışmaları büyük ilgi görmüştür. HTDA, bir metindeki her terim/nitelik hakkında ayrıntılı duygu ve düşüncelerin ortaya çıkarılmasını sağlar. HTDA yönteminin en önemli alt aşaması, bir metinden hedef terimlerinin çıkarılması işlemidir. Türkçe gibi sondan eklemeli dil yapılarına sahip metinlerde bu süreç daha da zorlaşmaktadır. Bu çalışmada, Türkçe kullanıcı yorumlarından hedef terimlerini çıkarmak için istatistiksel (TF-IDF), konu modelleme (LDA ve NMF) ve kural-tabanlı yöntemleri bir arada kullanan bir topluluk yaklaşımı önerilmiştir. Önerilen yöntem, farklı yöntemlerle elde edilen aday hedef terim kümelerini stratejik olarak birleştirir ve nihai hedef terimleri listesini belirler. Önerilen yöntem, Türkçe restoran yorumlarından oluşan SemEval-2016 HTDA kıyaslama veri seti üzerinde test edilmiştir. Önerilen yöntemin deneysel sonuçları aynı veri kümesi üzerinde yapılan önceki çalışmalarla karşılaştırılmıştır.

show abstract

Section: Preprocessing Of Textsmentioning

confidence: 99%

An ensemble approach for aspect term extraction in Turkish texts

Salur¹,

Aydın²,

JAMOUS³

2022

Pamukkale J Eng Sci

View full text Add to dashboard Cite

show abstract

“…Some scientific articles (the fourth group) deal with the analysis of international experien ces in the implementation of smart technologies on the territory of a number of countries and regions of the world, for example, Spain (Ballina, 2020; de Esteban Curiel et al, 2017; Gonzalez-Reverte, 2019) [29][30][31], Slovakia (Gajdosik, 2017) [32], Slovenia (Johnson et al, 2021) [33], Portugal (da Costa Liberato et al, 2018) [34], United Arab Emirates (Khan et al, 2017) [35], Montenegro (Podzharaya & Sochenkova, 2020) [36], Romania (Sabou & Maiorescu, 2020) [37], Turkey (Salur et al, 2019) [38], South Korea (Um & Chung, 2021) [39], China (Wang et al, 2013) [40], and in Chalkidiki (Avdimiotis & Tilikidou, 2017) [41].…”

Section: Brief Literature Reviewmentioning

confidence: 99%

Scientometric analysis of smart tourism using CiteSpace

Mamrayeva¹,

Tashenova²

2022

EA-XXI

View full text Add to dashboard Cite

This scientific article is devoted to the scientometric analysis of one of the new and relevant areas in economics – smart tourism, which has become widespread in the last 10-12 years. The research was conducted based on the using of materials from the Web of Knowledge database (Web of Science Core Collection: Science Citation Index Expanded, Social Science Citation Index, Arts and Humanities Citation Index Conference Proceedings Citation Index – Science, Conference Proceedings Citation Index – Social Science and Humanities Book Citation Index – Science, Book Citation Index – Social Science and Humanities, Emerging Sources Citation Index) for 2008-2022, which was later uploaded to CiteSpace 5.8.R3 to implement the tasks set in the research article: analysis of co-citations, including by authors; cluster analysis by keywords. It should be noted that the authors presented a capacious description of the WoS database array itself: from the perspective of the country component, institutes / universities / educational institutions and funding organizations, key sections, citation, types of documents, research area, Web of Science indexes / categories, etc. Also given a brief description of the authors whose work in the field of smart tourism is the most cited today. In general, it should be noted that the overall result of the search query «Smart Tourism» amounted to 724 documents, which were further used in the «Plain Text» format for scientometric analysis, which made it possible to determine the current and prospective areas of research in the field of smartification of tourism services, as well as build networks that visualize them visually. The author’s methodology for conducting scientometric analysis was also developed, starting from the moment the data array was received, and ending with the final visualization, which is universal, adaptive and complex, and can be used by any researcher when conducting a scientometric analysis of this kind in any of the branches of science, including in tourism.

show abstract

“…Aydoğan and Akcayol (2016), Özyurt and Akçayol (2018), Can and Alataş (2017) reviewed recent studies on sentiment analysis based on their methods, areas of application, and data sets. Considering these reviews and other research in the literature (Bilgin & Şentürk, 2017;Çoban et al, 2015;Kaynar et al, 2016;Kızılkaya, 2018;Meral & Diri, 2014;Salur et al, 2019;Toçoğlu, 2018;Türkmenoğlu, 2015), it is observed that the studies on sentiment analysis are often focused on the classification of examinations, tweets, or comments in a certain area using various machine learning techniques and the comparison of these classification results. It is also found that sentiment analysis studies in the context of tourism are quite limited and there are suggestions to conduct further analysis including Turkish content.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Turkish Sentiment Expressions About Touristic Sites Using Machine Learning

Aksu¹,

Karaman²

2021

Journal of Intelligent Systems: Theory and Applications

View full text Add to dashboard Cite

Analyzing data by inferring from unstructured data about customers is one of the main purposes of the tourism and many other industries as well. However, performing unstructured data analysis using traditional methods is quite inconvenient and costly. This can be overcome by using sentiment analysis, an area of application of text mining. Since there is no proven methodology for sentiment analysis, researchers often perform their studies by trial and error. Many studies on sentiment analysis have focused on comparing the preprocessing or the performance of various machine learning algorithms. Both for these reasons and since research on sentiment analysis with Turkish content is limited, this study aimed to determine the effects of labeling, stemming, and negation on the success of sentiment analysis using Turkish touristic site analysis. From the data set prepared for this study, 12 different variations were created according to labeling, number of classes, stemming, and negation. These data sets were classified using the algorithms Naive Bayes (NB), Multinominal Naive Bayes (MNB), k-Nearest Neighbor, and Support Vector Machines (SVM), often used in sentiment analyses, and the findings were compared.

show abstract

SmartSenti: A Twitter-Based Sentiment Analysis System for the Smart Tourism in Turkey

Cited by 14 publications

References 8 publications

An ensemble approach for aspect term extraction in Turkish texts

An ensemble approach for aspect term extraction in Turkish texts

Scientometric analysis of smart tourism using CiteSpace

Analysis of Turkish Sentiment Expressions About Touristic Sites Using Machine Learning

Contact Info

Product

Resources

About