in Batra, Punn, Sonbhadra, and Agarwal (2021) used BERT pre-trained model in the software engineering domain for sentiment analysis. Few works are found in literature about the app reviews based or software engineering perspective sentiment analysis. But the works of sentiment analysis in the context of software reviews are limited till now. There are several works available in machine learning and deep learning for sentiment analysis of website data, or blog information. The contributions of this work can be composed as follows: To design the system we use Sentiment Annotation of BERT base, hybridization of RNN, and LSTM to formulate an unbiased dataset of reviews. ![]() ![]() So, our aim is to design a system that calculates the actual rating from reviews, which guides developers to upgrade the version more precisely. To overcome this limitation we need to design a heuristic model. So, the actual impact of the new upgraded version may not be understandable through the rating system. Most of the users do not give ratings properly and many students give low ratings as they feel aversion about class. To upgrade the version of the Zoom Cloud Meetings App, the rating is becoming more important for developers. In the period of the pandemic, the authority released many upgraded versions of the Zoom application as per users’ reviews. Zoom is becoming one of the most popular platforms for online communication and learning. Everyone began to look for a platform that can help in the online classes, online meetings, and different services. During COVID-19 pandemic, global lockdowns forced people to work from home and students to continue academic study online. This outbreak of COVID-19 had a dramatic effect on world economics, because of the restriction and lockdown applied in different countries to slow down the spread. In 2019 COVID-19 creates a pandemic situation throughout the world. Zoom Cloud Meeting App is a video conference platform that is widely used as a learning media and communication platform through which people can meet anytime without an in-person presence. The results of our can provide more promising if we can use a large dataset only containing the reviews of the Zoom Cloud Meeting app. We use reviews of more than 250 apps from the Google Play app store. Our results found an average of 3.60 stars rating, where the actual average rating found in dataset is 3.08 stars. The results show that the reviews have more positive sentiments than the actual ratings. Out of four models trained on four different datasets, we found promising performance in two datasets containing a necessarily large amount of unbiased reviews. We use BERT-based sentiment annotation to create unbiased datasets and hybridize RNN with LSTM to find calculated ratings based on the unbiased reviews dataset. For this reason, we conduct this average rating calculation process based on the sentiment of user reviews to help software developers. And it has been the main problem to fix those bugs using user ratings for software developers. But most of the time the ratings and reviews are created contraposition between them because of the users’ inadvertent in giving ratings and reviews. To fix those bugs introduce developer needs users’ feedback based on the new release of the application. Which makes the chances to have lots of bugs during the release of new versions. For providing proper functionalities require in this situation of online supports the developers need the frequent release of new versions of the application. ![]() ![]() The online meeting app the “Zoom Cloud Meeting” provides the most entire supports for this purpose. All the educational institutes run their academic activities online. The recent outbreaks of the COVID-19 forced people to work from home.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |