2017/07/22 by Sandesh Swamy, Swamy, Sandesh, Alan Ritter +3 · 1 citation
Computer Science · Physics and Astronomy · Social Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Misinformation and Its Impacts #Opinion Dynamics and Social Influence #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1707.07212
openalex publication_date 2017/07/22 · openalex created_date 2022/09/21 · openalex updated_date 2026/07/28
Social media users often make explicit predictions about upcoming events.\nSuch statements vary in the degree of certainty the author expresses toward the\noutcome:"Leonardo DiCaprio will win Best Actor" vs. "Leonardo DiCaprio may win"\nor "No way Leonardo wins!". Can popular beliefs on social media predict who\nwill win? To answer this question, we build a corpus of tweets annotated for\nveridicality on which we train a log-linear classifier that detects positive\nveridicality with high precision. We then forecast uncertain outcomes using the\nwisdom of crowds, by aggregating users' explicit predictions. Our method for\nforecasting winners is fully automated, relying only on a set of contenders as\ninput. It requires no training data of past outcomes and outperforms sentiment\nand tweet volume baselines on a broad range of contest prediction tasks. We\nfurther demonstrate how our approach can be used to measure the reliability of\nindividual accounts' predictions and retrospectively identify surprise\noutcomes.\n