Previous psychophysiological research suggests that pain measurement needs to go beyond the assessment of Pain Intensity and Unpleasantness by adding the evaluation of Pain-Related Suffering. Based on this three-dimensional approach, we attempted to elucidate who is more likely to suffer by identifying reasons that may lead individuals to report Pain and Pain-Related Suffering more than others. A sample of 24 healthy participants (age range 18–33) underwent four different sessions involving the evaluation of experimentally induced phasic and tonic pain. We applied two decision tree models to identify variables (selected from psychological questionnaires regarding pain and descriptors from post-session interviews) that provided a qualitative characterization of the degrees of Pain Intensity, Unpleasantness and Suffering and assessed the respective impact of contextual influences. The overall classification accuracy of the decision trees was 75% for Intensity, 77% for Unpleasantness and 78% for Pain-Related Suffering. The reporting of suffering was predominantly associated with fear of pain and active cognitive coping strategies, pain intensity with bodily competence conveying strength and resistance and unpleasantness with the degree of fear of pain and catastrophizing. These results indicate that the appraisal of the three pain dimensions was largely determined by stable psychological constructs. They also suggest that individuals manifesting higher active coping strategies may suffer less despite enhanced pain and those who fear pain may suffer even under low pain. The second decision tree model revealed that suffering did not depend on pain alone, but that the complex rating-related decision making can be shifted by situational factors (context, emotional and cognitive). The impact of coping and fear of pain on individual Pain-Related Suffering may highlight the importance of improving cognitive coping strategies in clinical settings.
Conversational interfaces also called chatbots recently disrupted the Internet and opened up endless opportunities for assessment and learning. Formative feedback providing learners with a practical instruction for improvement is one of the challenging tasks in, for instance self-assessment settings and self-directed learning. This becomes even more challenging if user's personal information such as learning history and previous achievements cannot be exploited for data protection reasons or are simply not available. This study seeks to explore the opportunities of providing formative feedback in chatbot-based assessment. Two main challenges were faced: the limitations of the messenger as an interface that restricts visual representation of the quiz questions, and zero information about the user to generate adaptive feedback. Two types of feedback were investigated regarding their formative effect: immediate feedback, which was given after answering a question, and cumulative feedback detailing strengths and weaknesses of the user in each of the topics covered along with the directives for improvement. A chatbot called SQL Quizbot was deployed on Facebook Messenger for the purposes of this study 1. A survey conducted to disclose users' perception of the feedback reveals that more than 80% of the users find immediate feedback helpful. Overall this study shows that chatbots have a great potential as an aiding tool for e-learning systems to include an interactive component into feedback in order to increase user motivation and retention.
In this paper, we look beyond the traditional population-level sentiment modeling and consider the individuality in a person's expressions by discovering both textual and contextual information. In particular, we construct a hierarchical neural network that leverages valuable information from a person's past expressions, and offer a better understanding of the sentiment from the expresser's perspective. Additionally, we investigate how a person's sentiment changes over time so that recent incidents or opinions may have more effect on the person's current sentiment than the old ones. Psychological studies have also shown that individual variation exists in how easily people change their sentiments. In order to model such traits, we develop a modified attention mechanism with Hawkes process applied on top of a recurrent network for a userspecific design. Implemented with automatically labeled Twitter data, the proposed model has shown positive results employing different input formulations for representing the concerned information.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.