UNLOCKING CUSTOMER SENTIMENT INSIGHTS WITH AZURE SENTIMENT ANALYSIS: A COMPREHENSIVE REVIEW AND ANALYSIS
The paper analyzes the accuracy of the Azure Sentiment Analysis service for five languages, namely Romanian, French, Italian, Portuguese, and Spanish, and suggests that texts of moderate length are easier to classify.
Abstract
The paper analyzes the accuracy of the Azure Sentiment Analysis service for five languages, namely Romanian, French, Italian, Portuguese, and Spanish. The study generated 300 texts for each language type expressing positive and negative sentiments with varying lengths (less than 100 characters, between 100 and 250 characters, and more than 250 characters). The Azure Sentiment Analysis Review custom-made application was developed using C# language with .NET Framework and Entity Framework for the Microsoft SQL database, and it is used to make a request to the Azure Sentiment Service, and the response sets the label into the database. The expected and Azure labels for each type of analyzed text were described as well. The accuracy of sentiment recognition for different languages and text lengths is presented in the form of statistics, with the global accuracy of the service being 81.8%. The challenges of accurately classifying the sentiment of short and long texts were highlighted. The results suggest that texts of moderate length are easier to classify.