Abstract
Understanding how to assess the learners' evaluation has become an essential topic for both academics and practitioners as blended mobile learning applications have proliferated. This study examines users' sentiment and predicts the review rating of the blended learning platform app using machine learning (ML) techniques. The data for this study came from Google Play Store reviews of the Google Classroom app. The VADER and AFINN sentiment algorithms were used to determine if the filtered summary sentences were positive, neutral, or negative. In addition, five supervised machine learning algorithms were used to differentiate user evaluations of the Google Classroom app into three sentiment categories in the current study. According to the results of this investigation, the majority of reviews for this app were negative. While all five machine learning algorithms are capable of correctly categorizing review text into sentiment ratings, the random logistic regression outperforms in terms of accuracy.
TopIntroduction
In today's fast-paced world, information moves digitally between users, potentially influencing how other users interpret an event (Hossain et al., 2021). As a result, understanding public opinion is crucial (Daudert, 2021). Because Web 2.0 has given rise to blogs, forums, and online social networks, users may now discuss and share their opinions on any topic. They could, for example, express their unhappiness with a product they bought, talk about current events, or express their political views. Many applications (such as recommender systems), as well as corporate survey analysis and political campaign planning, rely on this type of user data (Dang et al., 2020). To put it another way, data is critical to the operation of every organization. In order to stay competitive or fall farther behind, data-driven decisions are becoming increasingly vital. In today's world, massive amounts of information may be acquired. However, manually acquiring and assessing data is extremely challenging (Aslam et al., 2020), necessitating the use of artificial intelligence (AI) to efficiently acquire and analyze large amounts of data. for example, 1,85,407 users' data will be acquired and reviewed in the present project, utilizing ML programming, which is a subset of AI.
A review is a piece of feedback given by a person who has either bought and utilized the product or service, or has had some other engagement with it. Customer feedback that is found on the internet is known as user reviews (Hossain and Rahman, 2022). Electronic user reviews are peer-generated product assessments and judgements published on a company's or third-party website such as the Google Play Store. User reviews lend weight to a decision and increase confidence in the person making it (Dwidienawati et al., 2020). In addition, Wang et al. (2021) suggested that increasing the quantity and quality of assessments increased a company's profitability. Online evaluations by customers have a significant impact on product and service income, according to Chevalier and Mayzlin (2006).
Smartphone applications have grown in popularity over the previous few years (Hassan et al., 2017). Mobile applications have tended to enhance people's capacities to execute daily chores and activities. The number of applications downloaded from app stores rises in lockstep with the number of smartphones in use throughout the world (Triantafyllou et al., 2020).
App platforms like the Google Play Store and others provide app developers with a one-of-a-kind user feedback mechanism in the form of app reviews. The Google Play Store is a digital distribution platform run by Google. In addition to apps, it sells other digital items such as e-books, movies, and music. Users may discover both paid and free programs in app stores. Paid apps must be purchased before they can be used, whereas free apps can be downloaded without charge. The Google Play store allows you to download and update apps manually or automatically (McIlroy et al., 2015). Aslam et al. (2020) also discussed how developers can keep track of their apps by using ratings and reviews. App evaluations include information about the user's experience, information about issues, suggestions for additional features, and a word rating of the app.
Key Terms in this Chapter
M-Learning: Also known as mobile learning, is a type of distance education that allows students to study in numerous situations through social and content exchanges on personal electronic devices such as smartphones.
APP: A mobile application, often known as a mobile app or just an app, is a computer program or software application that runs on a mobile device such a tablet, phone, or watch.
Review: A comment made by a customer who has bought and utilized the goods or service, or has had contact with it. User reviews are a type of user feedback seen on the internet.
Blended Learning Platform: Is a set of hardware, software, scheduling, and logistics that make up a learning program that includes online training or technology-assisted teaching.
Lexicon-Based Sentiment Analysis: A method of evaluating a document by aggregating the sentiment scores of all the words in the text, which is done using a sentiment lexicon that has already been produced.
Machine Learning: Is a sort of data analysis that uses artificial intelligence to automate the process of developing analytical models. It's a branch of AI based on the premise that robots can learn from data, discover patterns, and make judgments with little or no human involvement.
Emotion Analysis: Also known as sentiment analysis is a method of analyzing people's feelings. Natural language processing (NLP), biometrics, text analysis, and computational linguistics are used to identify, quantify, extract, and investigate emotional states and subjective data.