skip to main content

Title: Proposing an Open-Sourced Tool for Computational Framing Analysis of Multilingual Data
We propose a five-step computational framing analysis framework that researchers can use to analyze multilingual news data. The framework combines unsupervised and supervised machine learning and leverages a state-of-the-art multilingual deep learning model, which can significantly enhance frame prediction performance while requiring a considerably small sample of manual annotations. Most importantly, anyone can perform the proposed computational framing analysis using a free, open-sourced system, created by a team of communication scholars, computer scientists, web designers and web developers. Making advanced computational analysis available to researchers without a programming background to some degree bridges the digital divide within the communication research discipline in particular and the academic community in general.
; ; ; ; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
Digital journalism
Page Range or eLocation-ID:
1 - 22
Sponsoring Org:
National Science Foundation
More Like this
  1. When journalists cover a news story, they can cover the story from multiple angles or perspectives. These perspectives are called “frames,” and usage of one frame or another may influence public perception and opinion of the issue at hand. We develop a web-based system for analyzing frames in multilingual text documents. We propose and guide users through a five-step end-to-end computational framing analysis framework grounded in media framing theory in communication research. Users can use the framework to analyze multilingual text data, starting from the exploration of frames in user’s corpora and through review of previous framing literature (step 1-3) to frame classification (step 4) and prediction (step 5). The framework combines unsupervised and supervised machine learning and leverages a state-of-the-art (SoTA) multilingual language model, which can significantly enhance frame prediction performance while requiring a considerably small sample of manual annotations. Through the interactive website, anyone can perform the proposed computational framing analysis, making advanced computational analysis available to researchers without a programming background and bridging the digital divide within the communication research discipline in particular and the academic community in general. The system is available online at, via an API, or through our GitHub page
  2. International dark web platforms operating within multiple geopolitical regions and languages host a myriad of hacker assets such as malware, hacking tools, hacking tutorials, and malicious source code. Cybersecurity analytics organizations employ machine learning models trained on human-labeled data to automatically detect these assets and bolster their situational awareness. However, the lack of human-labeled training data is prohibitive when analyzing foreign-language dark web content. In this research note, we adopt the computational design science paradigm to develop a novel IT artifact for cross-lingual hacker asset detection(CLHAD). CLHAD automatically leverages the knowledge learned from English content to detect hacker assets in non-English dark web platforms. CLHAD encompasses a novel Adversarial deep representation learning (ADREL) method, which generates multilingual text representations using generative adversarial networks (GANs). Drawing upon the state of the art in cross-lingual knowledge transfer, ADREL is a novel approach to automatically extract transferable text representations and facilitate the analysis of multilingual content. We evaluate CLHAD on Russian, French, and Italian dark web platforms and demonstrate its practical utility in hacker asset profiling, and conduct a proof-of-concept case study. Our analysis suggests that cybersecurity managers may benefit more from focusing on Russian to identify sophisticated hacking assets. In contrast, financialmore »hacker assets are scattered among several dominant dark web languages. Managerial insights for security managers are discussed at operational and strategic levels.« less
  3. From a teacher’s perspective, teacher learning happens through a complex web of learning experiences. However, research on teacher professional development (PD) typically focuses on the direct influence of single activities or programs. PD researchers less often acknowledge the interactive impacts on teacher learning of the multiple experiences teachers have in different contexts. This conceptual paper works toward a more thoroughgoing ecological framing of teacher PD by bringing forth three dimensions of teacher learning that are often overlooked: scope, interconnectedness, and temporality. The essay centers on the type of design that is widely considered high-quality PD—namely, experiences that are collaborative and situated in teachers’ instructional context—and considers those experiences from the perspective of these three dimensions. I illustrate this framework and its affordances with data from a 4-year research project rooted in video-based mathematics teacher conversations. The focus on scope allows researchers to name and distinguish contexts that are salient to their different studies. The focus on interconnectedness uncovers the interactive relationship between the immediate and broader PD contexts. Finally, the focus on temporality affords the understanding of different phases in learning and extends linear conceptions of progress. Together, these dimensions provide a rich conceptualization to better inform the work ofmore »teacher educators.

    « less
  4. Background/Context: Bi/multilingual students’ STEM learning is better supported when educators leverage their language and cultural practices as resources, but STEM subject divisions have been historically constructed based on oppressive, dominant values and exclude the ways of knowing of nondominant groups. Truly promoting equity requires expanding and transforming STEM disciplines. Purpose/Objective/Research Question/Focus of Study: This article contributes to efforts to illuminate emergent bi/multilingual students’ ways of knowing, languaging, and doing in STEM. We follow the development of syncretic literacies in relation to translanguaging practices, asking, How do knowledges and practices from different communities get combined and reorganized by students and teachers in service of new modeling practices? Setting and Participants: We focus on a seventh-grade science classroom, deliberately designed to support syncretic literacies and translanguaging practices, where computer science concepts were infused into the curriculum through modeling activities. The majority of the students in the bilingual program had arrived in the United States at most three years before enrolling, from the Caribbean and Central and South America. Research Design: We analyze one lesson that was part of a larger research–practice partnership focused on teaching computer science through leveraging translanguaging practices and syncretic literacies. The lesson was a modeling and computing activitymore »codesigned by the teacher and two researchers about post–Hurricane María outmigration from Puerto Rico. Analysis used microethnographic methods to trace how students assembled translanguaging, social, and schooled practices to make sense of and construct models. Findings/Results: Findings show how students assembled representational forms from a variety of practices as part of accomplishing and negotiating both designed and emergent goals. These included sensemaking, constructing, explaining, justifying, and interpreting both the physical and computational models of migration. Conclusions/Recommendations: Implications support the development of theory and pedagogy that intentionally make space for students to engage in meaning-making through translanguaging and syncretic practices in order to provide new possibilities for lifting up STEM learning that may include, but is not constrained by, disciplinary learning. Additional implications for teacher education and student assessment practices call for reconceptualizing schooling beyond day-to-day curriculum as part of making an ontological shift away from prioritizing math, science, and CS disciplinary and language objectives as defined by and for schooling, and toward celebrating, supporting, and centering students’ diverse, syncretic knowledges and knowledge use.« less
  5. Recent years have witnessed an explosion of science conspiracy videos on the Internet, challenging science epistemology and public understanding of science. Scholars have started to examine the persuasion techniques used in conspiracy messages such as uncertainty and fear yet, little is understood about the visual narratives, especially how visual narratives differ in videos that debunk conspiracies versus those that propagate conspiracies. This paper addresses this gap in understanding visual framing in conspiracy videos through analyzing millions of frames from conspiracy and counter-conspiracy YouTube videos using computational methods. We found that conspiracy videos tended to use lower color variance and brightness, especially in thumbnails and earlier parts of the videos. This paper also demonstrates how researchers can integrate textual and visual features in machine learning models to study conspiracies on social media and discusses the implications of computational modeling for scholars interested in studying visual manipulation in the digital era. The analysis of visual and textual features presented in this paper could be useful for future studies focused on designing systems to identify conspiracy content on the Internet.