Search results

The purpose of this study is to propose a research model based on the stimulus-organism-response (S-O-R) model to examine whether media richness (MR), human-system interaction (HSI) and human-human interaction (HHI) as technological feature antecedents to medical professionals’ learning engagement (LE) can affect their learning persistence (LP) in massive open online courses (MOOCs).

Sample data for this study were collected from medical professionals at six university-/medical university-affiliated hospitals in Taiwan. A total of 600 questionnaires were distributed, and 309 (51.5%) usable questionnaires were analyzed using structural equation modeling in this study.

This study certified that medical professionals’ perceived MR, HSI and HHI in MOOCs positively affected their emotional LE, cognitive LE and social LE elicited by MOOCs, which together explained their LP in MOOCs. The results support all proposed hypotheses and the research model accounts for 84.1% of the variance in medical professionals’ LP in MOOCs.

This study uses the S-O-R model as a theoretical base to construct medical professionals’ LP in MOOCs as a series of the psychological process, which is affected by MR and interaction (i.e. HSI and HHI). Noteworthily, three psychological constructs, emotional LE, cognitive LE and social LE, are adopted to represent medical professionals’ organisms of MOOCs adoption. To date, hedonic/utilitarian concepts are more commonly adopted as organisms in prior studies using the S-O-R model and psychological constructs have received lesser attention. Hence, this study enriches the S-O-R model into an invaluable context, and this study’s contribution on the application of capturing psychological constructs for completely explaining three types of technological features as external stimuli to medical professionals’ LP in MOOCs is well-documented.

This study aims to conceptualize, rethink and systematize methods used for measurement and evaluation (M&E) corporate communication.

The reflection is based on 462 key English-language books and papers devoted to M&E in the fields of corporate communication and public relations from the 1970th to 2023. Keywords in the titles and abstracts found the necessary materials. A critical analysis of the central concepts, models and methods described in the literature was conducted. As a result, a new model that unifies and structures the M&E toolkit is proposed for discussion.

Despite the significant contribution to developing a wide range of M&E models, they are still not perfect and universal. In addition, this system of approaches is continuously self-evolving and changing under the influence of digital innovations, so it requires steady rethinking and updating. On the other hand, most previous studies focused on communication management processes, losing focus on communication aspects. This led to the need for an alternative view based on proven theories to fill this gap. The proposed model combines quantitative and qualitative M&E methods for the five main components of corporate communication (communicator, audience, content, channels and result), covering a wide range of tools, from statistical and sociological research to big data analysis and neuro research.

This work contributes to developing the M&E theory of corporate communication, systematizing existing methods and opening new research perspectives. From a practical point of view, companies can use the presented approach for a more accurate and objective internal evaluation of the main components of corporate communication.

Engaging in webcare, i.e. responding to online reviews, can positively affect consumer attitudes, intentions and behavior. Research is often scarce or inconsistent regarding the effects of specific webcare strategies on business performance. Therefore, this study tests whether and how several webcare strategies affect hotel bookings.

We apply machine learning classifiers to secondary data (webcare messages) to classify webcare variables to be included in a regression analysis looking at the effect of these strategies on hotel bookings while controlling for possible confounds such as seasonality and hotel-specific effects.

The strategies that have a positive effect on bookings are directing reviewers to a private channel, being defensive, offering compensation and having managers sign the response. Webcare strategies to be avoided are apologies, merely asking for more information, inviting customers for another visit and adding informal non-verbal cues. Strategies that do not appear to affect future bookings are expressing gratitude, personalizing and having staff members (rather than managers) sign webcare.

These findings help managers optimize their webcare strategy for better business results and develop automated webcare.

We look into several commonly used and studied webcare strategies that affect actual business outcomes, being that most previous research studies are experimental or look into a very limited set of strategies.

Sarcasm is a linguistic expression that usually carries the opposite meaning of what is being said by words, thus making it difficult for machines to discover the actual meaning. It is mainly distinguished by the inflection with which it is spoken, with an undercurrent of irony, and is largely dependent on context, which makes it a difficult task for computational analysis. Moreover, sarcasm expresses negative sentiments using positive words, allowing it to easily confuse sentiment analysis models. This paper aims to demonstrate the task of sarcasm detection using the approach of machine and deep learning.

For the purpose of sarcasm detection, machine and deep learning models were used on a data set consisting of 1.3 million social media comments, including both sarcastic and non-sarcastic comments. The data set was pre-processed using natural language processing methods, and additional features were extracted and analysed. Several machine learning models, including logistic regression, ridge regression, linear support vector and support vector machines, along with two deep learning models based on bidirectional long short-term memory and one bidirectional encoder representations from transformers (BERT)-based model, were implemented, evaluated and compared.

The performance of machine and deep learning models was compared in the task of sarcasm detection, and possible ways of improvement were discussed. Deep learning models showed more promise, performance-wise, for this type of task. Specifically, a state-of-the-art model in natural language processing, namely, BERT-based model, outperformed other machine and deep learning models.

This study compared the performance of the various machine and deep learning models in the task of sarcasm detection using the data set of 1.3 million comments from social media.

The aim of this study is first, to investigate the relative effect of user-generated content (UGC) and firm-generated content (FGC) on online brand advocacy, and second, to examine the mediation effect of customer engagement and the moderation effect of brand familiarity in the relationship between UGC and FGC and online brand advocacy. The differential impact of UGC and FGC on consumer behavior has yet to receive sufficient academic attention among hospitality scholars.

Based on social learning theory, cognitive consistency theory and schema theory, this study established an integrated research framework to explain the relationship between the constructs of the study. This study adopts a scenario-based experimental design in two separate studies within contexts to examine the proposed hypotheses.

The results revealed that UGC is a stronger predictor of online brand advocacy than FGC. A mediation analysis supported that the effect of digital content marketing types on online brand advocacy occurs because of customer engagement. Further, when the brand was familiar, participants showed a higher level of online brand advocacy than when they were exposed to FGC (vs. unfamiliar brand), whereas the effect of familiar and unfamiliar brands on online brand advocacy remains slightly close to each other when the participants were exposed to UGC. Brand familiarity positively enhanced participants’ engagement when they were exposed to UGC. Further, customer engagement is only a significant mediator when the brand is unfamiliar.

This paper presents significant managerial implications for hospitality companies about how they can effectively enhance brand advocacy in the online medium.

This research provides a novel contribution by examining the differential impact of UGC and FGC on online brand advocacy as well as uncovering the underlying mechanism of how and under what conditions user- and firm-generated content promotes online brand advocacy in the hospitality context.

Most previous studies predicting review helpfulness ignored the significance of deep features embedded in review text and instead relied on hand-crafted features. Hand-crafted and deep features have the advantages of high interpretability and predictive accuracy. This study aims to propose a novel review helpfulness prediction model that uses deep learning (DL) techniques to consider the complementarity between hand-crafted and deep features.

First, an advanced convolutional neural network was applied to extract deep features from unstructured review text. Second, this study used previous studies to extract hand-crafted features that impact the helpfulness of reviews and enhance their interpretability. Third, this study incorporated deep and hand-crafted features into a review helpfulness prediction model and evaluated its performance using the Yelp.com data set. To measure the performance of the proposed model, this study used 2,417,796 restaurant reviews.

Extensive experiments confirmed that the proposed methodology performs better than traditional machine learning methods. Moreover, this study confirms through an empirical analysis that combining hand-crafted and deep features demonstrates better prediction performance.

To the best of the authors’ knowledge, this is one of the first studies to apply DL techniques and use structured and unstructured data to predict review helpfulness in the restaurant context. In addition, an advanced feature-fusion method was adopted to better use the extracted feature information and identify the complementarity between features.

大多数先前预测评论有用性的研究忽视了嵌入在评论文本中的深层特征的重要性, 而主要依赖手工制作的特征。手工制作和深层特征具有高解释性和预测准确性的优势。本研究提出了一种新颖的评论有用性预测模型, 利用深度学习技术来考虑手工制作特征和深层特征之间的互补性。

首先, 采用先进的卷积神经网络从非结构化的评论文本中提取深层特征。其次, 本研究利用先前研究中提取的手工制作特征, 这些特征影响了评论的有用性并增强了其解释性。第三, 本研究将深层特征和手工制作特征结合到一个评论有用性预测模型中, 并使用Yelp.com数据集对其性能进行评估。为了衡量所提出模型的性能, 本研究使用了2,417,796条餐厅评论。

广泛的实验验证了所提出的方法优于传统的机器学习方法。此外, 通过实证分析, 本研究证实了结合手工制作和深层特征可以展现出更好的预测性能。

据我们所知, 这是首个在餐厅评论预测中应用深度学习技术, 并结合了结构化和非结构化数据来预测评论有用性的研究之一。此外, 本研究采用了先进的特征融合方法, 更好地利用了提取的特征信息, 并识别了特征之间的互补性。

The purpose of this study is to provide an in-depth understanding of the B2B customers’ perspective regarding salespeople’s social media use.

The study adopts a qualitative approach based on semi-structured interviews with 26 key informants performing their job in customer role in various industries.

The authors inductively identify five themes regarding the B2B customers’ perspective of social media use in B2B selling. These themes allow for valuable implications for social selling activities and expected outcomes.

Against a growing body of literature on drivers, best practices and outcomes of social media use by B2B salespeople, less attention has been paid to the customer’s side. The authors extend current research by providing a more complete picture of social selling activities and expected outcomes.