scholarly journals Sentiment Analysis of Students’ Feedback with NLP and Deep Learning: A Systematic Mapping Study

2021 ◽  
Vol 11 (9) ◽  
pp. 3986
Author(s):  
Zenun Kastrati ◽  
Fisnik Dalipi ◽  
Ali Shariq Imran ◽  
Krenare Pireva Nuci ◽  
Mudasir Ahmad Wani

In the last decade, sentiment analysis has been widely applied in many domains, including business, social networks and education. Particularly in the education domain, where dealing with and processing students’ opinions is a complicated task due to the nature of the language used by students and the large volume of information, the application of sentiment analysis is growing yet remains challenging. Several literature reviews reveal the state of the application of sentiment analysis in this domain from different perspectives and contexts. However, the body of literature is lacking a review that systematically classifies the research and results of the application of natural language processing (NLP), deep learning (DL), and machine learning (ML) solutions for sentiment analysis in the education domain. In this article, we present the results of a systematic mapping study to structure the published information available. We used a stepwise PRISMA framework to guide the search process and searched for studies conducted between 2015 and 2020 in the electronic research databases of the scientific literature. We identified 92 relevant studies out of 612 that were initially found on the sentiment analysis of students’ feedback in learning platform environments. The mapping results showed that, despite the identified challenges, the field is rapidly growing, especially regarding the application of DL, which is the most recent trend. We identified various aspects that need to be considered in order to contribute to the maturity of research and development in the field. Among these aspects, we highlighted the need of having structured datasets, standardized solutions and increased focus on emotional expression and detection.

Author(s):  
JARI VANHANEN ◽  
MIKA V. MÄNTYLÄ

Previous systematic literature reviews on pair programming (PP) lack in their coverage of industrial PP data as well as certain factors of PP such as infrastructure. Therefore, we conducted a systematic mapping study on empirical, industrial PP research. Based on 154 research papers, we built a new PP framework containing 18 factors. We analyzed the previous research on each factor through several research properties. The most thoroughly studied factors in industry are communication, knowledge of work, productivity and quality. Many other factors largely lack comparative data, let alone data from reliable data collection methods such as measurement. Based on these gaps in research further studies would be most valuable for development process, targets of PP, developers’ characteristics, and feelings of work. We propose how they could be studied better. If the gaps had been commonly known, they could have been covered rather easily in the previous empirical studies. Our results help to focus further studies on the most relevant gaps in research and design them based on the previous studies. The results also help to identify the factors for which systematic reviews that synthesize the findings of the primary studies would already be feasible.


2021 ◽  
Vol 11 (7) ◽  
pp. 2960
Author(s):  
Selina Demi ◽  
Ricardo Colomo-Palacios ◽  
Mary Sánchez-Gordón

The novel, yet disruptive blockchain technology has witnessed growing attention, due to its intrinsic potential. Besides the conventional domains that benefit from such potential, such as finance, supply chain and healthcare, blockchain use cases in software engineering have emerged recently. In this study, we aim to contribute to the body of knowledge of blockchain-oriented software engineering by providing an adequate overview of the software engineering applications enabled by blockchain technology. To do so, we carried out a systematic mapping study and identified 22 primary studies. Then, we extracted data within the research type, research topic and contribution type facets. Findings suggest an increasing trend of studies since 2018. Additionally, findings reveal the potential of using blockchain technologies as an alternative to centralized systems, such as GitHub, Travis CI, and cloud-based package managers, and also to establish trust between parties in collaborative software development. We also found out that smart contracts can enable the automation of a variety of software engineering activities that usually require human reasoning, such as the acceptance phase, payments to software engineers, and compliance adherence. In spite of the fact that the field is not yet mature, we believe that this systematic mapping study provides a holistic overview that may benefit researchers interested in bringing blockchain to the software industry, and practitioners willing to understand how blockchain can transform the software development industry.


IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 113878-113899 ◽  
Author(s):  
Jaafar Zubairu Maitama ◽  
Norisma Idris ◽  
Abubakar Zakari

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 20
Author(s):  
Boštjan Šumak ◽  
Saša Brdnik ◽  
Maja Pušnik

To equip computers with human communication skills and to enable natural interaction between the computer and a human, intelligent solutions are required based on artificial intelligence (AI) methods, algorithms, and sensor technology. This study aimed at identifying and analyzing the state-of-the-art AI methods and algorithms and sensors technology in existing human–computer intelligent interaction (HCII) research to explore trends in HCII research, categorize existing evidence, and identify potential directions for future research. We conduct a systematic mapping study of the HCII body of research. Four hundred fifty-four studies published in various journals and conferences between 2010 and 2021 were identified and analyzed. Studies in the HCII and IUI fields have primarily been focused on intelligent recognition of emotion, gestures, and facial expressions using sensors technology, such as the camera, EEG, Kinect, wearable sensors, eye tracker, gyroscope, and others. Researchers most often apply deep-learning and instance-based AI methods and algorithms. The support sector machine (SVM) is the most widely used algorithm for various kinds of recognition, primarily an emotion, facial expression, and gesture. The convolutional neural network (CNN) is the often-used deep-learning algorithm for emotion recognition, facial recognition, and gesture recognition solutions.


2019 ◽  
Vol 27 (03) ◽  
pp. 150-176
Author(s):  
Vinicius Dos Santos ◽  
Érica Ferreira De Souza ◽  
Kátia Romero Felizardo ◽  
Willian Massami Watanabe ◽  
Nandamudi Lankalapalli Vijaykumar ◽  
...  

Context: Conceptual Maps (CMs) have been used to organize knowledge and facilitate learning and teaching in multiple domains. CMs also are used in multiple settings in education, since they are able to clarify the relationships between the subcomponents of a particular topic. However, the construction of a CM requires time and effort in identifying and structuring knowledge. In order to mitigate this problem, Natural Language Processing (NLP) techniques have been employed and have contributed to automate the extraction of concepts and relationships from texts. Objective: This article summarizes the main initiatives of building CMs from NLP. Method: A systematic mapping study was used to identify primary studies that present approaches on the use of NLP to automatically create CMs. Results: The mapping provides a description of 23 available articles that have been reviewed in order to extract relevant information on a set of Research Questions (RQ). From the RQ results, a framework was designed in order to present how NLP could be employed to construct CMs. From this framework, a solution graph was elaborated to present different solutions paths to construct CMs using NLP. Conclusions: The construction of CMs using NLP is still a recent field, however, it has been proven to be effective in assisting the automatic construction of CMs.


Author(s):  
Wajdi Aljedaani ◽  
Anthony Peruma ◽  
Ahmed Aljohani ◽  
Mazen Alotaibi ◽  
Mohamed Wiem Mkaouer ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document