Providing a study on mathematics teachers' technological pedagogical content knowledge (TPACK), the goal of this chapter is to investigate the predictive value of teachers' beliefs (e.g., self-efficacy) and mathematical knowledge for teaching (MKT) on their level of TPACK. Background variables, gender, ethnicity, certification, experience, and mathematics degree were all controlled for in this study. Two-step regression analysis results by school level (K-5, middle, and high) indicate that standards-based mathematics teaching beliefs positively predict mathematics teachers' level of TPACK for all teachers. Having a college/graduate mathematics degree is more predictive of TPACK for K-5 and middle school teachers while MKT is more predictive of TPACK for high school teachers. In addition, elementary teachers' mathematics self-concept and pedagogical preparedness and middle school teachers' mathematics teaching interest were significantly related to their level of TPACK. The implications for school districts and teacher preparation programs to develop TPACK for teachers are discussed.
Sarcasm detection identifies natural language expressions whose intended meaning is different from what is implied by its surface meaning. It finds applications in many NLP tasks such as opinion mining, sentiment analysis, etc. Today, social media has given rise to an abundant amount of multimodal data where users express their opinions through text and images. Our paper aims to leverage multimodal data to improve the performance of the existing systems for sarcasm detection. So far, various approaches have been proposed that uses text and image modality and a fusion of both. We propose a novel architecture that uses the RoBERTa model with a co-attention layer on top to incorporate context incongruity between input text and image attributes. Further, we integrate feature-wise affine transformation by conditioning the input image through FiLMed ResNet blocks with the textual features using the GRU network to capture the multimodal information. The output from both the models and the CLS token from RoBERTa is concatenated and used for the final prediction. Our results demonstrate that our proposed model outperforms the existing state-of-the-art method by 6.14% F1 score on the public Twitter multimodal sarcasm detection dataset.
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.