[et_pb_section fb_built=”1″ admin_label=”section” _builder_version=”3.22″ global_colors_info=”{}”][et_pb_row admin_label=”row” _builder_version=”3.25″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”3.25″ global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text admin_label=”Text” _builder_version=”4.13.1″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” use_border_color=”off” border_color=”#ffffff” border_style=”solid” global_colors_info=”{}”]<\/p>\n
We work on multiple aspects of misinformation prevention, including:<\/p>\n
1. Detecting fake news automatically: <\/strong>Using text and visual features together with media theories to build machine learning based classifiers for fake news detection [1].<\/p>\n 2. Understanding COVID related conspiracy theories: <\/strong>Using Google autocomplete as a lens to understand how conspiracy related terms spread across the globe [2].<\/p>\n 3. Understanding the differences in COVID related autocompletes in English and Spanish: <\/strong>Systematically understanding the differences between Google search autocompletes in English and Spanish [3].<\/p>\n 4. Spam detection on Twitter:<\/strong> Understanding different modes of spam transmission over networks and identifying ways to detect them [4,5].<\/p>\n <\/strong><\/p>\n Related Publications <\/strong><\/p>\n <\/span><\/p>\n Fun<\/strong>ding and Support<\/strong><\/p>\n<\/li>\n<\/ol>\n We gratefully acknowledge the support from the National Science Foundation for this work.<\/p>\n 1. EAGER: SaTC: Early-Stage Interdisciplinary Collaboration: Fair and Accurate Information Quality Assessment Algorithm<\/a><\/p>\n 2. RAPID: Countering Language Biases in COVID-19 Search Auto-Completes<\/a><\/p>\n\n