Turkish-SAD

This repository provides a collection of Turkish Sentiment Analysis Datasets from 2012 to 2022, covering various domains. It includes access links for publicly available datasets and contact information for non-public datasets. It also includes a Python script for sentiment analysis using pre-trained transformer models.

Turkish Sentiment Analysis Datasets

A thorough investigation was carried out on research papers related to 'sentiment analysis' and 'Turkish dataset' indexed on Scopus between 2012 and 2022. 23 unique datasets were collected from publicly available sources and through email requests. This repository provides links to the publicly available Turkish datasets, as well as contact information for those that are not publicly available.

Search Details:

• Search Query: 'sentiment analysis' AND 'Turkish dataset'
• Fields: Article Title, Abstract, Keywords
• Date Range: 2012–2022
• Database: Scopus

The repository provides:

• Links to publicly available datasets.
• Contact Information for datasets not openly accessible.

---

Contents

1. List of Datasets
2. Usage
3. Requirements
4. Pre-trained Models
5. Using Google Colab

List of Datasets

Articles	Datasets	Status	Contact Info
Cross-lingual Polarity Detection with Machine Translation	Turkish Movie Reviews & Turkish Multidomain Products Reviews	Publicly Available	e.demirtas@student.tue.nl m.pechenizkiy@tue.nl
Sentiment Analysis in Turkish Media	Twitter Dataset & Movie Dataset	Not Available	turkmenogluc@itu.edu.tr tantug@itu.edu.tr
Sentiment Analysis for Turkish Twitter Feeds	Twt	Not Available	onder.coban@atauni.edu.tr baris.ozyer@atauni.edu.tr gulsah.ozyer@atauni.edu.tr
SentiWordNet for New Language: Automatic Translation Approach	Turkish Sentiment Analysis Dataset	Publicly Available	aucan@hacettepe.edu.tr n.behzad@hacettepe.edu.tr ebru@hacettepe.edu.tr sever@hacettepe.edu.tr
Sentiment Analysis on Microblog Data based on Word Embedding and Fusion Techniques	Turkish Sentiment Dataset	Publicly Available	ahayran@baskent.edu.tr msert@baskent.edu.tr
A Real-time Social Network-based Knowledge Discovery System for Decision Making	Foursquare Venue and Venue Comments Data	Publicly Available	asimyuksel@sdu.edu.tr
Words, Meanings, Characters in Sentiment Analysis	Dataset	Publicly Available	mfatih@ce.yildiz.edu.tr hakantaskopru77@gmail.com kubra.clskn94@gmail.com
Sentiment Analysis Through Transfer Learning for Turkish Language	Turkish Product Reviews Dataset	Publicly Available	emre.akin02@bilgiedu.net tugba.yildiz@bilgi.edu.tr
Sentiment Analysis in Turkish Text with Machine Learning Algorithms	Dataset	Not Available	merve.rumelli@ceng.deu.edu.tr deniz.akkus@ceng.deu.edu.tr ozge.kart@deu.edu.tr zerrin@cs.deu.edu.tr
Sentiment Analysis of Turkish Twitter Data	Dataset	Not Available	harisushehu@gmail.com stokat@pau.edu.tr md.sharif@uoh.edu.sa uyaver@tau.edu.tr
Comparison of N-stage Latent Dirichlet Allocation versus Other Topic Modeling Methods for Emotion Analysis	Dataset	Not Available	zekeriya.anil.guven@ege.edu.tr diri@yildiz.edu.tr txcakaloglu@ualr.edu
An Annotated Turkish Aspect Based Sentiment Analysis Corpus for Smart Tourism	Turkish Tourism ABSA Dataset	Publicly Available	mehmetumut.salur@gibtu.edu.tr iaydin@firat.edu.tr
Twitter Dataset and Evaluation of Transformers for Turkish Sentiment Analysis	BounTİ Turkish Sentiment Analysis	Publicly Available	abdullatif.koksal@boun.edu.tr arzucan.ozgur@boun.edu.tr
Aspect Based Twitter Sentiment Analysis on Vaccination and Vaccine Types in COVID-19 Pandemic With Deep Learning	Covid 19 Vaccination Dataset	Publicly Available	irfan.aygun@cbu.edu.tr bkaya@firat.edu.tr kaya@firat.edu.tr
TRSAv1: A New Benchmark Dataset for Classifying User Reviews on Turkish E-commerce Websites	TRSAv1	Publicly Available	m.aydogan@firat.edu.tr
Multi-Label Classification of E-Commerce Customer Reviews via Machine Learning	Turkish E-Commerce Reviews Dataset	Publicly Available	mustafacosar@hitit.edu.tr
Sentimental Analysis of Twitter Users from Turkish Content with Natural Language Processing	The Public Dataset & SentimentSet	Publicly Available	alok.mishra@himolde.no
A Dataset and BERT-based Models for Targeted Sentiment Analysis on Turkish Texts	Dataset	Not Available	melih.mutlu@boun.edu.tr arzucan.ozgur@boun.edu.tr
A Novel COVID-19 Sentiment Analysis in Turkish based on the Combination of Convolutional Neural Network and Bidirectional Long-short Term Memory on Twitter	COVID-19 Dataset	Not Available	talhakabakus@duzce.edu.tr
Opinion Mining Using LSTM Networks Ensemble for Multi-class Sentiment Analysis in E-commerce	Dataset	Not Available	dalnahas@infina.com.tr fasik@infina.com.tr akanturvardar@infina.com.tr mulkgun@infina.com.tr
BERT-based Transfer Learning Model for COVID-19 Sentiment Analysis on Turkish Instagram Comments	Dataset1 & Dataset2	Not Available	d2014242@mersin.edu.tr akdagli@mersin.edu.tr caci@mersin.edu.tr

Usage

Steps to Use:

1. Clone this repository:

   git clone https://github.com/sevvalckc/Turkish-SAD.git
   cd Turkish-SAD

2. Install required libraries: pip install -r requirements.txt
3. Ensure your datasets (e.g., data1.csv, data2.csv) are placed in the same directory as the script.
4. Run the script: python sentiment_analysis.py
5. The script will output sentiment analysis results to CSV files for each model.

Requirements

The script requires the following Python libraries and versions:

• Pandas version: 2.2.2
• PyTorch version: 2.5.1+cu121
• Transformers version: 4.46.2
• Scipy version: 1.13.1

Install Requirements

To install all required libraries, run: pip install -r requirements.txt sv) for each model.

Pre-trained Models Used

TurkishBERTweet: VRLLab/TurkishBERTweet-Lora-SA TSAM: emre/turkish-sentiment-analysis BERTurk: akoksal/bounti XLM-T: cardiffnlp/twitter-xlm-roberta-base-sentiment

Using Google Colab

Enabling TPU and High RAM

To use this script on Google Colab with TPU and high RAM, follow these steps:

• Open Google Colab: Go to Google Colab.
• Upload the script: Upload sentiment_analysis.py and your datasets (data1.csv, data2.csv) to Colab.

Enable TPU:

Go to Runtime > Change runtime type. Select TPU from the Hardware accelerator dropdown menu. Enable High RAM:

Go to Runtime > Manage sessions. Click on the current session. Select High-RAM from the options available.