An official website of the United States government
Empathy is a social mechanism used to support and strengthen emotional connection with others, including in online communities. However, little is currently known about the nature of these online expressions, nor the particular factors that may lead to their improved detection. In this work, we study the role of a specific and complex subcategory of linguistic phenomena, figurative language, in online expressions of empathy. Our extensive experiments reveal that incorporating features regarding the use of metaphor, idiom, and hyperbole into empathy detection models improves their performance, resulting in impressive maximum F1 scores of 0.942 and 0.809 for identifying posts without and with empathy, respectively.
more »
« less
Effects of Situational Factors on Metaphor Detection in an Online Discussion Forum
Accurate metaphor detection remains an open challenge. In this paper, we explore a new type of clue for disambiguating terms that may be used metaphorically or literally in an online medical support community. In particular, we investigate the influence of situational factors on propensity to employ the metaphorical sense of words when they can be used to illustrate the emotion behind the experience of the event. Specifically we consider the experience of stressful illness-related events in a poster’s recent history as situational factors. We evaluate the positive impact of automatically extracted cancer events on a metaphor detection task using data from an online cancer forum. We also provide a discussion of specific associations between events and metaphors, such as journey with diagnosis or warrior with chemotherapy.
more »
« less
- Award ID(s):
- 1302522
- PAR ID:
- 10080462
- Date Published:
- Journal Name:
- Third Workshop on Metaphor in NLP
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
For several years researchers have used the term "network orchestration" as a metaphor. In this paper, we make the metaphor reality; we describe a novel approach to network orchestration that leverages sounds to augment or replace various network management operations. We test our Music-Defined Networking approach with both a real and a virtual network testbed, on several mechanisms and applications: from datacenter server fan failure detection to authentication, from load balancing to explicit congestion notification and detection of heavy hitter flows. Our approach can be used with and without a Software-Defined Network controller. Despite its limitations, we believe that sound-based network management has potential to be further explored as an effective and inexpensive out-of-band orchestration technique.more » « less
-
de Vries, E. (Ed.)Historically, learning for young students has occurred in formal, in-person classroom environments. But in just a matter of weeks, children were mandated to transition to a completely new mode of learning, facing new learning challenges with heightened anxieties. To this end, we aim to better understand how our learning experience design (LXD) efforts support or hinder children’s engagement while participating in an online, video-based math course. This study operationalized LXD through the integration of e-learning instructional design (ID) as a lever for promoting students’ situational interest (SI), emphasis on human-centered design to support students’ user experience (UX), and the combination of SI and UX to foster student engagement in an online environment. Results provide practical implications for how we can intentionally iterate our designs to sustain children’s online engagement as we prepare for future instances of traditional, online and even hybrid models of instruction.more » « less
-
Driver reliance on automated vehicles (AV) is a critical component of safety particularly during high-risk traffic scenarios. Factors that influence reliance, including trust, situation awareness, fatigue, and demographics, have been independently explored; however, few analyses have investigated predicting AV reliance and compared factors comprehensively. The goals of this study were to develop a random forest (RF) model to predict reliance and to analyze the importance of factors for reliance decisions. We leveraged data from a driving simulation study where participants encountered four traffic events including responding to an illegal vehicle crossing, managing construction zones, stopping at a vandalized stop sign, and a pedestrian detection task. The dataset included reliance decisions and subjective assessments of dispositional trust, situational trust, fatigue, and workload. An RF model fit to the dataset using cross validation achieved an average AUC of 0.81 and accuracy of 0.77 and situational trust emerged as the most influential predictor.more » « less
-
At institutions with an emphasis on authentic research experiences as an integral part of the biology curriculum, COVID created a huge challenge for course instructors whose learning objectives were designed for such experiences. Moving such laboratory experiences online when remote learning became necessary has resulted in a new model for CUREs that utilizes free online databases to provide not only a novel research experience for students, but also the opportunity to engage in big data analysis. Cancer BioPortal (cBioPortal) is an open-access collective cancer research resource for storing and exploring clinical, genomic, proteomic, and transcriptomic data. cBioPortal eliminates the computational barrier of interpreting complex genomic data by providing easily understandable visualization that can be interpreted and translated into relevant biological insights. Because no prior computational knowledge is required, cBioPortal is an ideal educational tool for either in-person or distance learning environments. We developed a pedagogical approach, video tutorials, and data analysis workflows centered on using cBioPortal. Pedagogically, students develop an initial research outline that is continually updated and graded throughout the project. Progress during the project or course is assessed by a series of student presentations that are 5 to 15 minutes in length and are aimed at explaining the approach used in data acquisition, interpretation of the data, and relevance to the initial hypothesis. While cancer-specific, this analysis platform appeals to a wide range of classes and student interests. Further, the project has been successfully done both as an independent research experience and as part of a virtual class-based research project.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
