Leveraging User-Generated Comments and Fused BiLSTM Models to Detect and Predict Issues with Mobile Apps

In the last decade, technical advancements and faster Internet speeds have also led to an increasing number ofmobile devices and users. Thus, all contributors to society, whether young or old members, can use these mobileapps. The use of these apps eases our daily lives, and all customers who need any type of service can accessit easily, comfortably, and efficiently through mobile apps. Particularly, Saudi Arabia greatly depends on digitalservices to assist people and visitors. Such mobile devices are used in organizing daily work schedules and services,particularly during two large occasions, Umrah and Hajj. However, pilgrims encounter mobile app issues such asslowness, conflict, unreliability, or user-unfriendliness. Pilgrims comment on these issues on mobile app platformsthrough reviews of their experiences with these digital services. Scholars have made several attempts to solve suchmobile issues by reporting bugs or non-functional requirements by utilizing user comments.However, solving suchissues is a great challenge, and the issues still exist. Therefore, this study aims to propose a hybrid deep learningmodel to classify and predict mobile app software issues encountered by millions of pilgrims during the Hajj andUmrah periods from the user perspective. Firstly, a dataset was constructed using user-generated comments fromrelevant mobile apps using natural language processing methods, including information extraction, the annotationprocess, and pre-processing steps, considering a multi-class classification problem. Then, several experimentswere conducted using common machine learning classifiers, Artificial Neural Networks (ANN), Long Short-TermMemory (LSTM), and Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) architectures, toexamine the performance of the proposed model. Results show 96% in F1-score and accuracy, and the proposedmodel outperformed the mentioned models.

Development of Comment Correlation Matrix for Mobile Application Recommendation

As the evolution of mobile technology, mobile devices have become an essential tool in people＇s daily life. Moreover, with the rapid growth of Internet and mobile networks, people can easily access various services provided by mobile platforms. Many services can be executed on the mobile devices with various mobile applications launched to mobile platforms. People can choose what they like to install in their mobile devices and hence make their life more convenient, entertaining, and productive. However, there are too many mobile applications for users to choose. The goal of this research is to propose a methodology which can recommend top-N lists for mobile applications. A comment correlation matrix is proposed. Furthermore, a recommendation algorithm for mobile applications based on user comments and key attributes is built. With the proposed method, it outperforms Google play and is closer to user real feelings.

Entity perception of Two-Step-Matching framework for public opinions

Entity perception of ambiguous user comments is a critical problem of target identification for huge amount of public opinions.In this paper,a Two-Step-Matching method is proposed to identify the precise target entity from multiple entities mentioned.Firstly,potential entities are extracted by BiLSTM-CRF model and characteristic words by TF-IDF model from public comments.Secondly,the first matching is implemented between potential entities and an official business directory by Jaro-Winkler distance algorithm.Then,in order to find the pre-cise one,an industry-characteristic dictionary is developed into the second matching process.The precise entity is identified according to the count of characteristic words matching to industry-characteristic dictionary.In addition,associated rate(global indicator)and accuracy rate(sample indicator)are defined for evaluation of matching accuracy.The results for three data sets of public opinions about major public health events show that the highest associated rate and accuracy rate arrive at 0.93 and 0.95,averagely enhanced by 32%and 30%above the case of using the first matching process alone.This framework provides the method to find the true target entity of really wanted expression from public opinions.