Many brands utilize social media to communicate with consumers, but are they taking advantage of these media's potential for co-creation? We explore this in the corporate social responsibility (CSR) ...context where online CSR dialogs form as brands interact with consumers using social media. Study 1 examines eight brands' digital CSR communications on Twitter and suggests these dialogs are present but are rarely part of the process with most interactions between their consumers. Study 2 assesses the brands' CSR relevant tweets' content and finds that most are not relevant to CSR and, moreover, are predominantly one-way. Therefore, both studies reveal that brands are not tapping into the potential for co-creation that is inherent in social media. Thus, we recommend that social media communications should include (a) mentions of individual consumers, (b) audience specific and relevant message content, and (c) opportunities for consumers to co-create value with the relevant brands.
•Online CSR dialogs have the potential to create much value for stakeholders.•Network analysis metrics can measure CSR dialog engagement and characteristics.•Study 1 suggests that consumers are engaging with each other but rarely with brands.•Study 2 finds that studied brands' CSR communications lack engagement opportunities.•Brands should consider the engagement potential of social media to create value.
Our work explores the differences between GRU-based and transformer-based approaches in the context of sentiment analysis on text dialog. In addition to the overall performance on the downstream ...task, we assess the knowledge transfer capabilities of the models by applying a thorough zero-shot analysis at task level, and on the cross-lingual performance between five European languages. The ability to generalize over different tasks and languages is of high importance, as the data needed for a particular application may be scarce or non existent. We perform evaluations on both known benchmark datasets and a novel synthetic dataset for dialog data, containing Romanian call-center conversations. We study the most appropriate combination of synthetic and real data for fine-tuning on the downstream task, enabling our models to perform in low-resource environments. We leverage the informative power of the conversational context, showing that appending the previous four utterances of the same speaker to the input sequence has the greatest benefit on the inference performance. The cross-lingual and cross-task evaluations have shown that the transformer-based models possess superior transfer abilities to the GRU model, especially in the zero-shot setting. Considering its prior intensive fine-tuning on multiple labeled datasets for various tasks, FLAN-T5 excels in the zero-shot task experiments, obtaining a zero-shot accuracy of 51.27% on the IEMOCAP dataset, alongside the classical BERT that obtained the highest zero-shot accuracy on the MELD dataset with 55.08%.
•Context modeling for sentiment analysis in dialog systems.•Assess task transfer capabilities.•Assess language transfer capabilities.
Pregnancy establishment in mammals, including pigs, requires proper communication between embryos and the maternal reproductive tract. Prokineticin 1 (PROK1) has been described as a secretory protein ...with pleiotropic functions and as a novel tissue-specific angiogenic factor. However, despite the studies performed mainly on human cell lines and in mice, the function of PROK1 in the endometrium during early pregnancy is still not fully elucidated. We hypothesized that PROK1 contributes to pregnancy establishment in pigs. The present study is the first to report that the expression of PROK1 and its receptor (PROKR1) is elevated in the porcine endometrium during the implantation and early placentation period. PROK1 protein was detected mainly in luminal epithelial cells, glandular epithelial cells, and blood vessels in the endometrium. Using the porcine in vivo model of unilateral pregnancy, we revealed that conceptuses induced the endometrial expression of PROK1 and PROKR1. Moreover, the embryonic signal, estradiol-17β, as well as progesterone, stimulated the endometrial expression of PROK1 and PROKR1. We also evidenced that PROK1–PROKR1 signaling supports endometrial angiogenesis in pigs. The PROK1-stimulated proliferation of primary porcine endometrial endothelial (PEE) cells involved PI3K/AKT/mTOR, MAPK, cAMP, and NFKB signaling pathways. Furthermore, PROK1 via PROKR1 promoted the formation of capillary-like structures by PEE cells. PROK1 also stimulated VEGFA and PGF2α secretion, which in turn may indirectly support angiogenic changes within endometrial tissue. In summary, our study suggests that PROK1 acts as an embryonic signal mediator that regulates endometrial angiogenesis and secretory function during the implantation and early placentation period in pigs. Summary Sentence Prokineticin 1 is an embryonic signal mediator that, acting through PROKR1, promotes angiogenesis in the porcine endometrium during the implantation and early placentation period.
In this study, we delve into the perceived quality of recommendations provided by AI-based virtual service assistants (VSAs). Specifically, the role of the social presence of VSAs in influencing ...recommendation perceptions is investigated. We also explore how the social presence of a VSA is formed and how perceived anthropomorphism plays a vital role in shaping social presence and eventually instilling trust in VSAs among consumers. These relationships are examined in the context of online government services. The results indicate that consumer interaction with VSAs - manifesting via perceived anthropomorphism, social presence, dialog length, and attitudes - improves recommendation quality perceptions, which further instills trust in VSA-based recommendations. Perceived anthropomorphism was found to strongly influence the formation of social presence, whereas trust and recommendation quality - the outcomes of social presence - were found to be partially conditional on the dialog length and the degree of positive attitudes toward VSAs. The findings additionally suggest that a VSA can be considered a social actor that possesses the capability to bring a “human touch” to online services, therefore improving the overall online service experience.
•VSA as a social actor improves the overall online service experience.•Social presence increases recommendation quality and trust in the VSA.•Perceived anthropomorphism influences the formation of social presence.•Attitudes toward VSAs moderate the effects of social presence.•Dialog length moderates the social presence-trust relationship.
In real-world dialog systems, the ability to understand the user’s emotions and interact anthropomorphically is of great significance. Emotion Recognition in Conversation (ERC) is one of the key ways ...to accomplish this goal and has attracted growing attention. How to model the context in a conversation is a central aspect and a major challenge of ERC tasks. Most existing approaches struggle to adequately incorporate both global and local contextual information, and their network structures are overly sophisticated. For this reason, we propose a simple and effective Dual-stream Recurrence-Attention Network (DualRAN), which is based on Recurrent Neural Network (RNN) and Multi-head ATtention network (MAT). DualRAN eschews the complex components of current methods and focuses on combining recurrence-based methods with attention-based ones. DualRAN is a dual-stream structure mainly consisting of local- and global-aware modules, modeling a conversation simultaneously from distinct perspectives. In addition, we develop two single-stream network variants for DualRAN, i.e., SingleRANv1 and SingleRANv2. According to the experimental findings, DualRAN boosts the weighted F1 scores by 1.43% and 0.64% on the IEMOCAP and MELD datasets, respectively, in comparison to the strongest baseline. On two other datasets (i.e., EmoryNLP and DailyDialog), our method also attains competitive results.
•Dialog systems (DS) allow intuitive interaction through natural language.•Dialog managers are usually implemented ad hoc and difficult to adapt to new domains.•A statistical methodology is proposed ...to reduce the effort required to develop and adapt dialog managers.•User simulation is also proposed to facilitate the acquisition of the required dialog corpus.•A complete implementation of our proposal for different dialog systems and its evaluation are also detailed.
This paper proposes a domain-independent statistical methodology to develop dialog managers for spoken dialog systems. Our methodology employs a data-driven classification procedure to generate abstract representations of system turns taking into account the previous history of the dialog. A statistical framework is also introduced for the development and evaluation of dialog systems created using the methodology, which is based on a dialog simulation technique. The benefits and flexibility of the proposed methodology have been validated by developing statistical dialog managers for four spoken dialog systems of different complexity, designed for different languages (English, Italian, and Spanish) and application domains (from transactional to problem-solving tasks). The evaluation results show that the proposed methodology allows rapid development of new dialog managers as well as to explore new dialog strategies, which permit developing new enhanced versions of already existing systems.
In this paper, we describe RavenClaw, a plan-based, task-independent dialog management framework. RavenClaw isolates the domain-specific aspects of the dialog control logic from domain-independent ...conversational skills, and in the process facilitates rapid development of mixed-initiative systems operating in complex, task-oriented domains. System developers can focus exclusively on describing the dialog task control logic, while a large number of domain-independent conversational skills such as error handling, timing and turn-taking are transparently supported and enforced by the RavenClaw dialog engine. To date, RavenClaw has been used to construct and deploy a large number of systems, spanning different domains and interaction styles, such as information access, guidance through procedures, command-and-control, medical diagnosis, etc. The framework has easily adapted to all of these domains, indicating a high degree of versatility and scalability.
The widespread development of conversational agents (chatbots) has enabled us to communicate and collaborate with different forms and functions of robots using natural language, thus facilitating a ...closer relationship between humans and technology. Given that chatbot services infused with domain knowledge are of great interest to not only global businesses but also academics, chatbots have in recent years become a popular research topic in the field of natural language processing. We therefore aim at improving current chatbots with the addition of natural emotions. In contrast to previous work, we intend to distinguish fine-grained emotion differences between words in order to better understand emotion expressions in sentences. Our approach infuses fine-grained emotion content into the response generation process to make the dialog more emotionally resonant. The experimental results demonstrate that this method can classify emotions more effectively. In addition, the proposed hybrid model, which consists of recurrent and convolutional neural networks with additional emotion-specific valence-arousal features, can correctly identify five emotions with a 67.89% overall F1-score. We further evaluate the subjective quality of the responses and discover that the infusion of fine-grained emotion information substantially improves the quality and fluency of automatically generated empathetic conversation. We conclude that the proposed model can greatly improve the efficiency and usability of a conversational chatbot system.
•We propose an integrated framework to improve current chatbots with natural emotions. Unlike previous work, we intend to distinguish fine emotion difference between words in order to better understand the sentential emotion.•Our proposed approach avoids the intense work of human annotation and infuse the fine emotions into response generation process automatically.•The proposed novel approach that contains a sequence-to-sequence structure with an encoder and a decoder to produce responses to a piece of text, and an emotion detection model to distill the most suitable sentence as the final response.•Experimental results show that the emotion detection module can achieve state-of-the-art outcomes when predicting valence and arousal values, and encoding finer emotion information into generation module is proven to assist in the ability to create fluent and logical sentence with appropriate emotion content.•This study provides some observations regarding human preferences in emotional responses. These results can serve as guidelines for future research on the design of a more natural dialog system.
This volume collects works by Hispanists from different origins: from researchers whose mother tongue is Spanish and who carry out their work in the Hispanic world, whether peninsular or American, to ...those who work in regions where Spanish is a minority language and/or or who have acquired Spanish as a second language. This joyous diversity finds its expression in the works that make up this volume, highlighting one of the central objectives of the AIH: the academic and plural dialogue between the Hispanicisms of the world, an enriching and vivifying dialogue that knows no borders. Doing so for the first time outside of Europe and America takes on a very special significance, by inserting this multiplicity of perspectives into the present and much-needed dialogue between our peoples and regions. The printed book exclusively includes the opening speeches and plenary presentations, which were given by Myrna Solotorevsky, Patrizia Botta, Angela Schrott, Juan Diego Vila, Manuel Rivero Rodríguez and James Valender. The other papers are in open access