Search results

This paper aims to propose a method for automatically labelling an affective lexicon with intensity values by using the WordNet Similarity (WS) software package with the purpose of improving the results of an affective analysis process, which is relevant to interpreting the textual information that is available in social networks. The hypothesis states that it is possible to improve affective analysis by using a lexicon that is enriched with the intensity values obtained from similarity metrics. Encouraging results were obtained when an affective analysis based on a labelled lexicon was compared with that based on another lexicon without intensity values.

The authors propose a method for the automatic extraction of the affective intensity values of words using the similarity metrics implemented in WS. First, the intensity values were calculated for words having an affective root in WordNet. Then, to evaluate the effectiveness of the proposal, the results of the affective analysis based on a labelled lexicon were compared to the results of an analysis with and without affective intensity values.

The main contribution of this research is a method for the automatic extraction of the intensity values of affective words used to enrich a lexicon compared with the manual labelling process. The results obtained from the affective analysis with the new lexicon are encouraging, as they provide a better performance than those achieved using a lexicon without affective intensity values.

Given the restrictions for calculating the similarity between two words, the lexicon labelled with intensity values is a subset of the original lexicon, which means that a large proportion of the words in the corpus are not labelled in the new lexicon.

The practical implications of this work include providing tools to improve the analysis of the feelings of the users of social networks. In particular, it is of interest to provide an affective lexicon that improves attempts to solve the problems of a digital society, such as the detection of cyberbullying. In this case, by achieving greater precision in the detection of emotions, it is possible to detect the roles of participants in a situation of cyberbullying, for example, the bully and victim. Other problems in which the application of affective lexicons is of importance are the detection of aggressiveness against women or gender violence or the detection of depressive states in young people and children.

This work is interested in providing an affective lexicon that improves attempts to solve the problems of a digital society, such as the detection of cyberbullying. In this case, by achieving greater precision in the detection of emotions, it is possible to detect the roles of participants in a situation of cyber bullying, for example, the bully and victim. Other problems in which the application of affective lexicons is of importance are the detection of aggressiveness against women or gender violence or the detection of depressive states in young people and children.

The originality of the research lies in the proposed method for automatically labelling the words of an affective lexicon with intensity values by using WS. To date, a lexicon labelled with intensity values has been constructed using the opinions of experts, but that method is more expensive and requires more time than other existing methods. On the other hand, the new method developed herein is applicable to larger lexicons, requires less time and facilitates automatic updating.

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.

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.

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.

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.

As a distinctive form of communist heritage tourism, the ideology and government-led form of red tourism warrants an in-depth examination of how tourists consume and perceive it. This study aims to reveal tourists’ perception of red tourism through the lens of destination image.

This study collected 9,819 user-generated photographs within four types of red tourism destinations (RTDs) and used a computer visual and semiotic analysis approach to conduct photograph-based cognitive and affective attributes extraction. Network analysis further visualized the co-relations between cognitive images and affective images. ANOVA analysis compared the differences of the four types of destination images.

Ten dimensions of cognitive image and eight categories of affective image of red tourism were identified. It found that monuments, statues, memorial symbols were the distinctive cognitive features, and admiration was the most dominant emotion. Heterogeneity of destination images was identified among the four types of RTDs.

To the best of the authors’ knowledge, the study is one of the first to explore tourists’ consumption of red tourism through the lens of destination image, which reveals the inconsistencies between the officially projected images and tourists’ perceived images of red tourism. Using Plutchik’s model, it validates a series of positive and negative emotions contributing to the affective images of red tourism, which expands the findings of emotions within the extant red tourism research. Through combined applications of computer visual and semiotic analysis, ANOVA, network analysis and model visualization, the study provides an important methodological triangulation for photograph-based destination image studies.

红色旅游作为共产主义旅游的独特形式, 游客如何感知这种国家意识形态植入与政府主导型旅游值得深入研究。本研究旨在从目的地意象视角揭示游客红色旅游感知。

本研究收集四种类型的红色旅游地9819张用户生成照片, 利用计算机视觉-情感析法对照片进行认知和情感元素提取。复杂网络分析揭示了认知意象与情感意象之间的关联。方差分析比较了四种红色旅游地意象的差异。

本研究确定了红色旅游认知意象的十个维度和情感意象的八个类别。研究发现, 纪念碑、雕像、纪念符号是其独特的认知意象元素, 钦佩是其最主要的情感，四种类型红色旅游地意象存在差异性。

本文是同类研究中首次从目的地意象视角探索游客对红色旅游地感知, 揭示了红色旅游官方投射意象与游客感知意象之间的差异。利用Plutchik情感之轮模型, 验证了一系列积极和消极情绪构成红色旅游地情感意象, 拓展了红色旅游的情感发现。综合运用计算机视觉-情感分析、方差分析、网络分析和模型可视化等方法, 为基于照片的旅游目的地意象研究提供了一个重要方法。

Como forma distintiva del turismo del patrimonio comunista, la ideología y la forma gubernamental del turismo rojo justifican un examen en profundidad de cómo lo consumen y perciben los turistas. Este estudio pretende revelar la percepción que tienen los turistas del turismo rojo desde la perspectiva de la imagen del destino.

Este estudio recopiló 9.819 fotografías generadas por los usuarios dentro de cuatro tipos de destinos de turismo rojo, y utilizó un enfoque de análisis visual y semiótico por ordenador para llevar a cabo la extracción de atributos cognitivos y afectivos basados en fotografías. El análisis de redes visualizó además las correlaciones entre las imágenes cognitivas y las imágenes afectivas. El análisis ANOVA comparó las diferencias de los cuatro tipos de imágenes de destino.

Se identificaron diez dimensiones de imagen cognitiva y ocho categorías de imagen afectiva del turismo rojo. Se descubrió que los monumentos, las estatuas y los símbolos conmemorativos eran los rasgos cognitivos distintivos, y la admiración la emoción más dominante. Se identificó una heterogeneidad de imágenes de destino entre los cuatro tipos de destinos de turismo rojo.

El estudio es uno de los primeros en explorar el consumo de turismo rojo por parte de los turistas a través de la lente de la imagen del destino, lo que revela las incoherencias entre las imágenes proyectadas oficialmente y las imágenes percibidas por los turistas del turismo rojo. Utilizando el modelo de Plutchik, valida una serie de emociones positivas y negativas que contribuyen a las imágenes afectivas del turismo rojo, lo que amplía los hallazgos sobre las emociones dentro de la investigación existente sobre el turismo rojo. Mediante aplicaciones combinadas de análisis visual y semiótico por ordenador, ANOVA, análisis de redes y visualización de modelos, el estudio proporciona una importante triangulación metodológica para los estudios de la imagen del destino basados en fotografías.

This paper aims to explore whether consumers' cognitive reactions to a branded product remain stable over time. In many created concepts, entity attributes are such that cognitive reactions to them change in a predictable manner by attraction to elements of novelty and typicality in the genre. By analysing products from a luxury vehicle brand, under the framework of a theoretical model of changing “affective content”, this paper seeks to explore whether brands behave similarly.

The study draws on research previously published into the changing nature of art, poetry, architecture and other artistic genres. Text from motoring press articles written contemporarily to the production of products of the brand, over the past 80 years, are analysed for constructs of affective content and the overall values expressed.

The results provide evidence that the attributes of some branded products produce cognitive conditions that cycle in a manner that is predictable, with change points corresponding to new product introductions.

Through understanding cognitive reactions to the branded product that may be discreetly deconstructable and anticipated, advantageous product attribute development can progress with some certainty. Further, new product launches can be timed to coincide with receptive consumer conditions supported by appropriate attribute emphasis.

This paper applies a theory, which has been proven to exist in a number of artistic genres, to the brand for the first time. Its contribution is twofold; firstly, to expand developing knowledge into the cognitive processing of the branded product; and secondly, to introduce an informative process to product and brand development activities.

The paper aims to offer an approach that allows an analysis and construction of a typology of virtual city brand co-creation practices.

The approach is illustrated by using data collected in regard to the branding of Stockholm; it is based on visual representations expressing the process in which brand co-creation unfolds in a network of different affective modalities.

Virtual representations emerge as expressive trans-locations that obtain communicative qualities in which practices are included and also in which practices are constituted. Practices represent how experiencing is carried out by different stakeholders’ relationships and emotional interactions. They are labeled as contributing, using, esteeming and opposing. These practices constitute analytical abstraction that represent different power plays between the visual and material content of the images, the technologies of production and the display and performance of the virtual.

The focus on practices suggests a way to perform a critical analysis that could be used to research the performative process of co-creating brands in a way that the practices offer signals that can be used to grasp the dynamism of the process. Further, it suggests that the analysis of the practices in the virtual realm has the potential to unfold the material, nonlinear dynamic of communication that resides beyond forms of meaning and cognition.

The offered approach posits an alternative view of co-creation in which the process is uncontrollable by any stakeholders involved; the process might therefore not have a start and end or it could start everywhere in the internet and can transform at any point in space-time.

It contributes to the research on performative place branding by problematizing the issue of agency. It does so by displaying the way in which the process of virtual city brand co-creation could be analyzed based on practices involving the co-construction of visualization and materialization. Analytically, by dealing with virtual representations where practices of brand co-creation unfold, such an approach also helps to unpack the consequences of those practices and can highlight the technologies that are used and the specific qualities of the visual objects enacted.

Dyadic interactions are significant for human life. Most body sensor networks-based research studies focus on daily actions, but few works have been done to recognize affective actions during interactions. The purpose of this paper is to analyze and recognize affective actions collected from dyadic interactions.

A framework that combines hidden Markov models (HMMs) and k-nearest neighbor (kNN) using Fisher kernel learning is presented in this paper. Furthermore, different features are considered according to the interaction situations (positive situation and negative situation).

Three experiments are conducted in this paper. Experimental results demonstrate that the proposed Fisher kernel learning-based framework outperforms methods using Fisher kernel-based approach, using only HMMs and kNN.

The research may help to facilitate nonverbal communication. Moreover, it is important to equip social robots and animated agents with affective communication abilities.

The presented framework may gain strengths from both generative and discriminative models. Further, different features are considered based on the interaction situations.

Attempts to demonstrate how a shared vision amongst group members is developed. Endeavours to understand the process through which members of a multicultural group, Asian and Western, develop and sustain a consensus, the way they interpret, give meaning and make sense of what went on during the process of strategic decision making. Explores the cross‐cultural differences in cognitive perception, affective and communicative dimensions. Suggests that findings show these categories as highly interrelated and determine the shared vision.

Addressing the continuing productivity challenge, the purpose of this paper is to analyze data from the National Health Service on employee involvement (EI) in order to gain critical insights into how employees’ shared perception of EI in organizational decision making (i.e. EI climate) might address two persistent issues: how to enhance positive staff attitudes and improve organizational performance. In doing so, the authors respond to recent calls for more multilevel research and extend previous research on EI climate by attending to both EI climate level and EI climate strength.

Data from 4,702 employees nested in 33 UK hospitals were used to test the moderating role of EI climate strength in the cross-level EI climate level employee level-attitudes relationship and in the organizational-level EI climate-organizational effectiveness relationship.

The results of the multilevel analyses showed that EI climate level was positively associated with individual-level employee attitudes (i.e. job satisfaction, organizational commitment). Further the results of the hierarchical regression analysis and the ordinal logistic regression analysis showed that EI climate level was also related to organizational effectiveness (i.e. lower outpatient waiting times, higher performance quality). In addition, both analyses demonstrated the moderating role of EI climate strength, in that the positive impact of EI climate level on employee attitudes and organizational effectiveness was more marked in the presence of a strong climate compared to a weak EI climate.

By creating and maintaining a positive and strong climate for involvement, hospital managers can tackle the productivity challenge that UK hospitals and health care institutions more generally are currently facing while improving the attitudes of their employees who are critical in the transformative process and ultimately underpin the organizational success.

This is the first study which provides evidence that favorable and consistent collective recognition of EI opportunities by staff contributes to enhance both employee attitudes and hospital performance. Results highlight the role of EI climate strength and underscore its importance in future research and practice.

The purpose of this study is expected to reveal the relationship between organizational commitment and turnover intention in the tourism and hospitality literature with more generalizable results, and thus, provide researchers with a new perspective for future studies. In this context, Individual studies that examined the relationship between organizational commitment and turnover intention in the tourism and hospitality industry were systematically identified by a comprehensive literature review.

Individual studies were synthesized and analyzed via a meta-analysis method to reveal whether any relationship exists between organizational commitment and turnover intention and to estimate the direction and intensity of the relationship in a more reliable and comprehensive manner. The analyses were carried out on 13 scientific papers that met the inclusion criteria.

Results showed that a moderate negative relationship exists between organizational commitment and turnover intention of employees in the tourism and hospitality industry. In this context, individuals who have emotional commitments to their institutions will have lower turnover intentions than others. The right personal selection, performance evaluation techniques, promotion, training and development opportunities, career opportunities and talent management and functional virtues such as strong communication, trust and justice will not only reinforce organizational commitment but also attract talented individuals to an organization and ensure employee retention.

In the current study, individual studies focusing on the relationship between organizational commitment and turnover were cumulatively collected, synthesized and analyzed. By way of providing a review of individual studies, the study provides cumulative and reliable evidence to the literature regarding the relationship between organizational commitment and turnover, and hence, contributes to the further progression of the field. The study is also the first meta-analysis carried out on the subject in question.