Turkish Sentiment Classification Model

This model is created with the intent of classifying positive or negative sentiment in any Turkish text data and labeling thousands of rows.

About Model
Nowadays, most of the people in the marketing and research world are familiar with the terms of social media monitoring, brand monitoring, the voice of the customer, customer service, and market research. With all these terms, sentiment analysis shines and becomes a game-changer that provides an essential insight into consumers' thoughts and feelings. This Turkish Sentiment Classification Model enables you to get more meaningful analysis by classifying your data as "positive" or "negative." It means less manual work and more time to take action.
About Training Set
The data was collected by using Kimola's Analytics platform from social media. It was chosen from different industries and topics, then labeled as "positive" and "negative."The primary step of preparing this training set was to determine if a sentence contains a "positive" or "negative" feeling. Also, attention was paid to divide the sentences with opposite sentiment and remove proper names such as brand names, company names, and celebrity names. Now, the training dataset has 8,326 rows of data. It was trained many times by using cross-validation and tested eight times in total. Also, the development process of this model is still on and on.

$75 credit to explore Kimola Cognitive for 45 days!

Built for marketing and research professionals. No programming skills are required!