Search results

1 – 10 of over 5000
To view the access options for this content please click here
Article
Publication date: 18 October 2021

Saurabh Kumar

Decision-making in human beings is affected by emotions and sentiments. The affective computing takes this into account, intending to tailor decision support to the…

Abstract

Purpose

Decision-making in human beings is affected by emotions and sentiments. The affective computing takes this into account, intending to tailor decision support to the emotional states of people. However, the representation and classification of emotions is a very challenging task. The study used customized methods of deep learning models to aid in the accurate classification of emotions and sentiments.

Design/methodology/approach

The present study presents affective computing model using both text and image data. The text-based affective computing was conducted on four standard datasets using three deep learning customized models, namely LSTM, GRU and CNN. The study used four variants of deep learning including the LSTM model, LSTM model with GloVe embeddings, Bi-directional LSTM model and LSTM model with attention layer.

Findings

The result suggests that the proposed method outperforms the earlier methods. For image-based affective computing, the data was extracted from Instagram, and Facial emotion recognition was carried out using three deep learning models, namely CNN, transfer learning with VGG-19 model and transfer learning with ResNet-18 model. The results suggest that the proposed methods for both text and image can be used for affective computing and aid in decision-making.

Originality/value

The study used deep learning for affective computing. Earlier studies have used machine learning algorithms for affective computing. However, the present study uses deep learning for affective computing.

Details

Journal of Enterprise Information Management, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1741-0398

Keywords

To view the access options for this content please click here
Article
Publication date: 5 June 2017

Atika Qazi, Ram Gopal Raj, Glenn Hardaker and Craig Standing

The purpose of this paper is to map the evidence provided on the review types, and explain the challenges faced by classification techniques in sentiment analysis (SA)…

Downloads
2425

Abstract

Purpose

The purpose of this paper is to map the evidence provided on the review types, and explain the challenges faced by classification techniques in sentiment analysis (SA). The aim is to understand how traditional classification technique issues can be addressed through the adoption of improved methods.

Design/methodology/approach

A systematic review of literature was used to search published articles between 2002 and 2014 and identified 24 papers that discuss regular, comparative, and suggestive reviews and the related SA techniques. The authors formulated and applied specific inclusion and exclusion criteria in two distinct rounds to determine the most relevant studies for the research goal.

Findings

The review identified nine practices of review types, eight standard machine learning classification techniques and seven practices of concept learning Sentic computing techniques. This paper offers insights on promising concept-based approaches to SA, which leverage commonsense knowledge and linguistics for tasks such as polarity detection. The practical implications are also explained in this review.

Research limitations/implications

The findings provide information for researchers and traders to consider in relation to a variety of techniques for SA such as Sentic computing and multiple opinion types such as suggestive opinions.

Originality/value

Previous literature review studies in the field of SA have used simple literature review to find the tasks and challenges in the field. In this study, a systematic literature review is conducted to find the more specific answers to the proposed research questions. This type of study has not been conducted in the field previously and so provides a novel contribution. Systematic reviews help to reduce implicit researcher bias. Through adoption of broad search strategies, predefined search strings and uniform inclusion and exclusion criteria, systematic reviews effectively force researchers to search for studies beyond their own subject areas and networks.

Details

Internet Research, vol. 27 no. 3
Type: Research Article
ISSN: 1066-2243

Keywords

To view the access options for this content please click here
Article
Publication date: 28 August 2020

Manning Li, Patrick Y.K. Chau and Lin Ge

Inspired by the dynamic changes in our daily lives enabled via quantified-self technologies and the urgent need for more studies on the human-computer interaction design…

Abstract

Purpose

Inspired by the dynamic changes in our daily lives enabled via quantified-self technologies and the urgent need for more studies on the human-computer interaction design mechanisms adopted by these applications, this study explores the value of user affective experience mirroring and examines the empowerment effect of meaningful gamification in a psychological self-help system (PSS) that aids people in work stress relief.

Design/methodology/approach

Based on an analysis of the existing systems and theories in relevant fields, we conducted mixed-method research, involving semi-structured interviews, experience sampling experiments and user bio data triangulations, to identify the benefits of user affective experience mirroring and examine the impact of visual impact metaphor–based (VIM) meaningful gamification on PSS users.

Findings

For a gamified PSS, users generally perceive VIM as arousing more feelings of enjoyment, empathy, trust and usefulness, empowering them to gain more mastery and control over their emotional well-beings, especially with relieving their occupational stress and upbringing their level of perceived happiness. Overtime, VIM-based meaningful gamification further boosts such value of a PSS.

Research limitations/implications

Weaving together meaningful gamification and psychological empowerment theories, the results emphasized that successful empowerment of user through gamification in PSSs relies heavily on whether a deeper and meaningful affective connection can be established with the users, in short, “meaningful gamification for psychological empowerment”. Such an understanding, as demonstrated in our research framework, also sheds light on the design theories for persuasive technology and human influence tactics during human computer interactions.

Practical implications

The results of the study demonstrate to practitioners how to make the best use of gamification strategies to deeply relate to and resonate with users. Even without complicated game-play design, meaningful gamification mechanisms, such as VIM facilitate the empowerment of users while gaining their appreciation, establishing a deeper connection with them and eventually generating persuasive effects on intended future behavioural outcomes.

Social implications

The effective management of work-related stress with handy tools such as a VIM-based PSS can be beneficial for many organizations and, to a large extent, the society.

Originality/value

This study proposed and empirically demonstrated the empowerment effect of meaningful gamification for PSS users. In this cross-disciplinary study, theories from different research domains were synthesized to develop a more thorough and multi-faceted understanding of the optimal design strategies for emerging information systems like this VIM-based PSS.

To view the access options for this content please click here
Book part
Publication date: 9 September 2019

Devanathan Sudharshan

Abstract

Details

Organic Growth Disciplines
Type: Book
ISBN: 978-1-78973-875-9

To view the access options for this content please click here
Article
Publication date: 15 November 2017

Louise Spiteri and Jen Pecoskie

The purpose of this paper is to provide an examination of emotional experiences, particularly how they are situated in the readers’ advisory (RA) literature and the…

Abstract

Purpose

The purpose of this paper is to provide an examination of emotional experiences, particularly how they are situated in the readers’ advisory (RA) literature and the literatures from a variety of outside disciplines in order to create taxonomies of affect from this context.

Design/methodology/approach

The approach of this study is twofold. First, this work reviews the literature on affect in Library and Information Science (LIS) and ancillary disciplines in order to understand the definition of affect. Second, using extant taxonomies and resources noted from the literature review, taxonomies are created for three aspects of affect: emotions, tones, and associations.

Findings

This paper contextualises and defines affect for the LIS discipline. Further, a result of the work is the creation of three taxonomies through an RA lens by which affective experiences can be classified. The resulting three taxonomies focus on emotion, tone, and associations.

Practical implications

The taxonomies of emotion, tone, and associations can be applied to the practical work of bibliographic description, helping to expand access and organisation through an affective lens. These taxonomies of affect could be used by readers’ advisors to help readers describe their desired reading experiences. As the taxonomies have been constructed from an RA perspective, and can be applied to the RA literature, they could expand the understanding of RA theory, especially that of appeal.

Originality/value

This study furthers the exploration of affect in LIS and provides tangible taxonomies of affect for the LIS discipline in an RA context, which have not been previously produced.

Details

Journal of Documentation, vol. 74 no. 2
Type: Research Article
ISSN: 0022-0418

Keywords

To view the access options for this content please click here
Article
Publication date: 19 June 2017

Pedro Isaias, Francisco Reis, Clara Coutinho and Jose Alberto Lencastre

This paper examines the acceptance, of a group of 79 students, of an educational forum, used for mobile and distance learning, that has been modified to include empathic…

Downloads
1370

Abstract

Purpose

This paper examines the acceptance, of a group of 79 students, of an educational forum, used for mobile and distance learning, that has been modified to include empathic characteristics and affective principles.

Design/methodology/approach

With this study is proposed that the introduction of empathic and affective principles in educational forums is a useful and effective way to increase students’ participation and motivation in educational contexts. After an analysis of existing literature and research on the subject of empathic technology, the unified theory of acceptance and use of technology (UTAUT) was used as a framework for the research model. The analysis of their acceptance is done via an extended version of the UTAUT that focuses on the use of the variable attitude toward technology and uses gender, age and experience as moderators. A partial least square technique has been used to test the nine hypotheses.

Findings

The results confirmed three of the nine hypotheses: performance expectancy and effort expectancy had a positive influence on the students attitudes towards empathic forums, while the effect of social influence and facilitating conditions was considered insignificant; social influence had a positive influence on the students’ behavioral intention to use emphatic forums, while attitude toward technology, performance expectancy, facilitating conditions and effort expectancy were considered not relevant.

Originality/value

The focus of this study was the influence of attitude toward empathic forums, used for mobile and distance learning, and the results establish the grounds for future research on attitude as an important determinant of technology acceptance.

Details

Interactive Technology and Smart Education, vol. 14 no. 2
Type: Research Article
ISSN: 1741-5659

Keywords

To view the access options for this content please click here
Article
Publication date: 16 August 2011

Stephen Rainey and Philippe Goujon

The purpose of this paper is to criticise ad hoc approaches to ethics in research and development in technology as descriptive and non‐ethical, and based upon a narrow…

Downloads
1385

Abstract

Purpose

The purpose of this paper is to criticise ad hoc approaches to ethics in research and development in technology as descriptive and non‐ethical, and based upon a narrow conception of rationality.

Design/methodology/approach

The approach deploys a theory of normativity that can incorporate values and a broad conception of rationality, in order to account for the relevance of issues for the addressees of normative injunctions.

Findings

A normative approach is possible and required in order to implement ethics in research and development in technology.

Originality/value

The approach draws together themes from current alternative approaches that each fail to deploy the full resources of the normative approach, and so fail to fully account for ethics. This approach identifies and moves beyond present limited approaches.

Details

Journal of Information, Communication and Ethics in Society, vol. 9 no. 3
Type: Research Article
ISSN: 1477-996X

Keywords

Content available
Book part
Publication date: 1 May 2019

Arturas Kaklauskas, Irene Lill, Dilanthi Amaratunga and Ieva Ubarte

This article’s purpose is to develop The Model for Smart, Self-learning and Adaptive Resilience Building (SARB).

Abstract

Purpose

This article’s purpose is to develop The Model for Smart, Self-learning and Adaptive Resilience Building (SARB).

Design/Methodology/Approach

Products and patents of methods and systems analysis was carried out in the fields of BIM application, Smart, Self-learning and Adaptive Resilience Building. Based on other researchers’ findings, The SARB Model was proposed.

Findings

Analysis of the literature showed that traditional decisions on the informational modelling do not satisfy all the needs of smart building technologies owing to their static nature. The SARB Model was developed to take care of its efficiency from the brief stage to the end of its service life.

Research Limitations/Implications

The SARB Model was developed to take care of its efficiency from the brief stage to the end of its service life. The SARB Model does have some limitations: (1) the processes followed require the collection of much unstructured and semi-structured data from many sources, along with their analyses to support stakeholders in decision-making; (2) stakeholders need to be aware of the broader context of decision-making and (3) the proposal is process-oriented, which can be a disadvantage during the model’s implementation.

Practical Implications

Two directions can be identified for the practical implications of the SARB Model. The initial expectation is the widespread installation of SARB Model within real estate and construction organisations. Furthermore, development of the SARB Model will be used to implement the ERASMUS+ project, “Advancing Skill Creation to ENhance Transformation—ASCENT” Project No. 561712-EPP-1-2015-UK-EPPKA2-CBHE-JP.

Originality/Value

The practical implications of this paper are valuable.

Details

10th Nordic Conference on Construction Economics and Organization
Type: Book
ISBN: 978-1-83867-051-1

Keywords

To view the access options for this content please click here
Article
Publication date: 20 June 2008

Alex Bennet and David Bennet

The purpose of this paper is to explore the role of emotion in learning, specifically, e‐learning and its relationship to the phenomenon called energetic learning.

Downloads
2775

Abstract

Purpose

The purpose of this paper is to explore the role of emotion in learning, specifically, e‐learning and its relationship to the phenomenon called energetic learning.

Design/methodology/approach

After first presenting operation definitions, the paper looks through the lens of new findings in neuroscience to build an understanding of the role of emotions in learning, then focuses specifically on how e‐learning systems contribute to energetic learning, providing examples of e‐learning platforms and software programs currently available that have specific attributes contributing to energetic learning.

Findings

With technology comes a natural excitement in terms of connectivity and its support of self‐driven, experiential learning which is part of the evolutionary heritage. As the understanding of the neuroscience and biology of human learning advances, the personal needs of individual learners are being begun to understand better. Bringing these needs together with e‐learning system capabilities will offer a significant jump in the learning rate and efficiency as we move into a future filled with change, uncertainty, complexity and anxiety.

Originality/value

The paper introduces the concept of energetic learning with specific focus on the contribution of e‐learning to energetic learning.

Details

VINE, vol. 38 no. 2
Type: Research Article
ISSN: 0305-5728

Keywords

To view the access options for this content please click here
Article
Publication date: 7 June 2013

Kuan Cheng Lin, Tien‐Chi Huang, Jason C. Hung, Neil Y. Yen and Szu Ju Chen

This study aims to introduce an affective computing‐based method of identifying student understanding throughout a distance learning course.

Downloads
1323

Abstract

Purpose

This study aims to introduce an affective computing‐based method of identifying student understanding throughout a distance learning course.

Design/methodology/approach

The study proposed a learning emotion recognition model that included three phases: feature extraction and generation, feature subset selection and emotion recognition. Features are extracted from facial images and transform a given measument of facial expressions to a new set of features defining and computing by eigenvectors. Feature subset selection uses the immune memory clone algorithms to optimize the feature selection. Emotion recognition uses a classifier to build the connection between facial expression and learning emotion.

Findings

Experimental results using the basic expression of facial expression recognition research database, JAFFE, show that the proposed facial expression recognition method has high classification performance. The experiment results also show that the recognition of spontaneous facial expressions is effective in the synchronous distance learning courses.

Originality/value

The study shows that identifying student comprehension based on facial expression recognition in synchronous distance learning courses is feasible. This can help instrutors understand the student comprehension real time. So instructors can adapt their teaching materials and strategy to fit with the learning status of students.

1 – 10 of over 5000