SentiWordNet for New Language: Automatic Translation Approach

Uçan, Alaettin; Naderalvojoud, Behzad; Sezer, Ebru Akçapınar; Sever, Hayri

doi:10.1109/sitis.2016.57

Cited by 20 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They evaluated their results with Fm using 5-fold CV and got the best results with QER. Movie and hotel datasets were prepared and used in [33]. They proposed an automatic translation approach to create a lexicon for a new language.…”

Section: Resultsmentioning

confidence: 99%

“…Dataset Technique Results [37] Twitter NB Acc: 62.6% [37] Twitter NB + active learning Acc: 64% [38] Twitter Logistic regression + QER Fm: 0.779 [33] Movie…”

Section: Methodsmentioning

confidence: 99%

“…In this study, experiments are done by using three different datasets to evaluate the results of the methodology on different types of data. Movie review and hotel review datasets are downloaded from the Hacettepe University Multimedia Information Retrieval Group's website [33]. Movie reviews on this website are collected from beyazperde.com and hotel reviews are collected from otelpuan.com.…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

A hybrid sentiment analysis method for Turkish

Erşahin¹,

Aktaş²,

Kılınç³

et al. 2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper presents a hybrid methodology for Turkish sentiment analysis, which combines the lexicon-based and machine learning (ML)-based approaches. On the lexicon-based side, we use a sentiment dictionary that is extended with a synonyms lexicon. Besides this, we tackle the classification problem with three supervised classifiers, naive Bayes, support vector machines, and J48, on the ML side. Our hybrid methodology combines these two approaches by generating a new lexicon-based value according to our feature generation algorithm and feeds it as one of the features to machine learning classifiers. Despite the linguistic challenges caused by the morphological structure of Turkish, the experimental results show that it improves the accuracy by 7% on average.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Dataset Technique Results [37] Twitter NB Acc: 62.6% [37] Twitter NB + active learning Acc: 64% [38] Twitter Logistic regression + QER Fm: 0.779 [33] Movie…”

Section: Methodsmentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid sentiment analysis method for Turkish

Erşahin¹,

Aktaş²,

Kılınç³

et al. 2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…This empirical study compares the traditional BoW (or VSM) based ML algorithms and newly proposed BERT in terms of empirical achievement. In order to evaluate performances of the two approaches, we chose diverse six datasets from literature as cyberbullying identification [32], sentiment analysis of Turkish movie and hotel reviews [33], spam Short Message Service (SMS) detection [34], a text classification dataset of six news categories [35] and emotion recognition dataset with six emotion categories [36]. In particular, the mentioned Turkish datasets are studied in the literature and they have morphological language processing steps with corresponding BoW-ML results as baseline.…”

Section: Introductionmentioning

confidence: 99%

Advancing natural language processing (NLP) applications of morphologically rich languages with bidirectional encoder representations from transformers (BERT): an empirical case study for Turkish

et al. 2021

View full text Add to dashboard Cite

Language model pre-training architectures have demonstrated to be useful to learn language representations. bidirectional encoder representations from transformers (BERT), a recent deep bidirectional self-attention representation from unlabelled text, has achieved remarkable results in many natural language processing (NLP) tasks with fine-tuning. In this paper, we want to demonstrate the efficiency of BERT for a morphologically rich language, Turkish. Traditionally morphologically difficult languages require dense language pre-processing steps in order to model the data to be suitable for machine learning (ML) algorithms. In particular, tokenization, lemmatization or stemming and feature engineering tasks are needed to obtain an efficient data model to overcome data sparsity or high-dimension problems. In this context, we selected five various Turkish NLP research problems as sentiment analysis, cyberbullying identification, text classification, emotion recognition and spam detection from the literature. We then compared the empirical performance of BERT with the baseline ML algorithms. Finally, we found enhanced results compared to base ML algorithms in the selected NLP problems while eliminating heavy pre-processing tasks.

show abstract

“…The consequent statistics results through the prediction service are displayed on the real‐time reporting and a dashboard software developed to monitor the system. HUMIR data set, which is a set of hotel and movie reviews collected from two well‐known recommendation web sites, is used to train and test NB model for SA.…”

Section: Introductionmentioning

confidence: 99%

A spark‐based big data analysis framework for real‐time sentiment prediction on streaming data

Kılınç

2019

Softw Pract Exp

View full text Add to dashboard Cite

Summary There are many data sources that produce large volumes of data. The Big Data nature requires new distributed processing approaches to extract the valuable information. Real‐time sentiment analysis is one of the most demanding research areas that requires powerful Big Data analytics tools such as Spark. Prior literature survey work has shown that, though there are many conventional sentiment analysis researches, there are only few works realizing sentiment analysis in real time. One major point that affects the quality of real‐time sentiment analysis is the confidence of the generated data. In more clear terms, it is a valuable research question to determine whether the owner that generates sentiment is genuine or not. Since data generated by fake personalities may decrease accuracy of the outcome, a smart/intelligent service that can identify the source of data is one of the key points in the analysis. In this context, we include a fake account detection service to the proposed framework. Both sentiment analysis and fake account detection systems are trained and tested using Naïve Bayes model from Apache Spark's machine learning library. The developed system consists of four integrated software components, ie, (i) machine learning and streaming service for sentiment prediction, (ii) a Twitter streaming service to retrieve tweets, (iii) a Twitter fake account detection service to assess the owner of the retrieved tweet, and (iv) a real‐time reporting and dashboard component to visualize the results of sentiment analysis. The sentiment classification performances of the system for offline and real‐time modes are 86.77% and 80.93%, respectively.

show abstract

SentiWordNet for New Language: Automatic Translation Approach

Cited by 20 publications

References 13 publications

A hybrid sentiment analysis method for Turkish

A hybrid sentiment analysis method for Turkish

Advancing natural language processing (NLP) applications of morphologically rich languages with bidirectional encoder representations from transformers (BERT): an empirical case study for Turkish

A spark‐based big data analysis framework for real‐time sentiment prediction on streaming data

Contact Info

Product

Resources

About