Abstract:The ability to exploit public sentiment in social media is increasingly considered as an important tool for market understanding, customer segmentation and stock price prediction for strategic marketing planning and manoeuvring. This evolution of technology adoption is energised by the healthy growth in big data framework, which caused applications based on Sentiment Analysis (SA) in big data to become common for businesses. However, scarce works have studied the gaps of SA application in big data. The contribution of this paper is two-fold: (i) this study reviews the state of the art of SA approaches. including sentiment polarity detection, SA features (explicit and implicit), sentiment classification techniques and applications of SA and (ii) this study reviews the suitability of SA approaches for application in the big data frameworks, as well as highlights the gaps and suggests future works that should be explored. SA studies are predicted to be expanded into approaches that utilise scalability, possess high adaptability for source variation, velocity and veracity to maximise value mining for the benefit of the users.
Sentiment analysis is an evolving field of a study that deals directly with the online expressions posted by the user via the Internet with the main objective to automate the process of mining opinions into valuable information. For online reviews, this analysis deals with the identification of positive and negative reviews to help the consumer and the distributor in the decision-making process. In text analysis tasks, such as text classification and sentiment analysis, the appropriate choice of term weighting schemes will have a huge impact on the effectiveness of the analysis. This paper explores the effect of using term weighting scheme in the sentiment classification of online movie reviews. Specifically, the researchers applied Support Vector Machine (SVM) with linear and non-linear kernels to perform the classification process. The main finding of this study was that LinearSVC when used with TF-IDF improved the classification performance by as much as 87%. Thus, LinearSVC, together with TF-IDF, can serve as an effective technique in the extraction process of online documents.
Feature extraction and selection are critical in sentiment analysis (SA) to extract and select only the appropriate features by removing those deemed redundant. As such, the successful implementation of this process leads to better classification accuracy. Inevitably, selecting high-quality minimal features can be challenging given the inherent complication in dealing with over-fitting issues. Most of the current studies used a heuristic method to perform the classification process that will result in selecting and examining only a single feature subset, while ignoring the other subsets that might give better results. This study explored the effect of using the meta-heuristic method together with the ensemble classification method in the sentiment classification of online reviews. Adding to that point, the extraction and selection of relevant features used feature ranking, hyper-parameter optimization, crossover, and mutation, while the classification process utilized the ensemble classifier. The proposed method was tested on the polarity movie review dataset v2.0 and product review dataset (books, electronics, kitchen, and music). The test results indicated that the proposed method significantly improved the classification results by 94%, which far exceeded the existing method. Therefore, the proposed feature extraction and selection method can help in improving the performance of SA in online reviews and, at the same time, reduce thenumber of extracted features.
Objectives: The main aim of this study was to investigate the factors that influence students’, academicians’, clients’, as well as developer’s preferences in choosing their preferred approach in system development, namely structured analysis design (SAD) or object-oriented analysis and design (OOAD). Methods: The research design was based on a survey methodology and a case study. For the survey, questionnaires were administered to 30 students and 38 academicians, who were randomly selected from several Malaysian universities. For the case study, the requirements of the information system were modeled and presented to several clients to elicit their feedback. The survey data were analyzed using SPSS Findings: The result shows that students preferred the use of OOAD approach, which clearly outnumbered those who preferred the SAD approach, which stood at 33%. Interestingly, the majority (53%) of academicians preferred the use of a mixture of both approaches. Likewise, the clients shared a similar view with the academicians, whereas the developer preferred the OOAD approach. Application/Improvements: Clearly, the findings suggest that both approaches are essential, but the one that is widely used by developers and preferred by students is OOAD, and thus should be given priority when it comes to structured analysis and design. As such, curriculum designers and institutions of higher learning, particularly those offering system analysis and design and related courses, should make the necessary changes to the existing curriculum such that the academic programs offered will be able to produce highly competent and skilled analysts and designers as required by the industry.
Perkembangan teknologi sentiasa berkait rapat dengan perkembangan sistem pendidikan. Pembangunan koswer MyInterval ini adalah bertujuan untuk membantu pelajar memahami topik dengan lebih mudah dan dapat memberikan pelajar merasai pengalaman pembelajaran yang menyeronokkan dengan gabungan elemen multimedia. Objektif utama dalam pembangunan koswer ini adalah untuk membangunkan koswer yang mengandungi elemen multimedia yang mampu membantu pelajar muzik dalam topik Interval bagi kursus Aural 1. Metodologi yang digunakan dalam pembangunan koswer ini adalah Model Hanifin dan Peck. Koswer yang telah lengkap dibangunkan, diuji kepada 21 responden yang terpilih. Responden kajian ini terdiri daripada seorang pensyarah dan 20 pelajar UPSI yang mengambil jurusan Pendidikan Muzik. Kajian ini dijalankan bagi mengetahui keberkesanan hasil akhir produk yang telah dibangunkan. Hasil kajian mencatatkan min keseluruhan bagi kebolehgunaan koswer adalah pada tahap yang sangat tinggi iaitu sebanyak 4.35. Maklum balas daripada responden adalah positif. Responden menyatakan pembangunan koswer adalah sangat menarik dan dapat membantu pelajar untuk kemahiran Aural dalam Muzik. Selain itu, Dari segi teks, pemilihan teks adalah bersesuaian dan pemilihan konsep permainan (interval games) juga adalah menarik. Hasil dapatan kajian menunjukkan bahawa koswer MyInterval yang dibangunkan dapat membantu pensyarah dan pelajar dalam memahami topik dengan lebih baik. Dapat disimpulkan bahawa koswer MyInterval ini telah mendapat respon yang baik dan positif dan sesuai untuk dijadikan sebagai alat bantu mengajar kerana kandungan dan elemen multimedia yang disediakan adalah menarik dan mudah untuk difahami. Development of an Interactive Courseware “MyInterval” in the Topic of Intervals for Music Education Students at UPSIThe development of technology is always closely related to the development of the education system. The aim of developing MyInterval courseware is to help students to understand the topic easier as well as providing a fun learning experience with a combination of multimedia elements. The main objective developing this courseware is to develop a courseware that contains multimedia elements which can help music students in the interval topic for the Aural 1 course. The methodology used in the developing MyInterval course by using the Hanafin and Peck model. The completed courseware was tested on 21 selected respondents. The data were analysed with a sample of one lecturer and 20 UPSI students majoring in Music Education as the respondents. This study was conducted to investigate on the effectiveness of the final product of the courseware that has been developed. By the analysis, the overall mean of study conducted on the usability of the courseaware was at a very high level which is 4.35. The feedback from respondents was positive. Respondents stated that the courseware developed was interesting and helps students with the Aural skills in Music. In terms of text, simple text selection was appropriate. The game concept (interval games) was also interesting. The findings show the MyInterval courseware developed helps lecturers and students in understanding the topic much better. As per conclude, MyInterval courseware has received good and positive response and can be used as a teaching tool because the content and multimedia elements provided are interesting and easy to understand.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.