Soroush Vosoughi

The spread of true and false news online

Lies spread faster than the truth There is worldwide concern over false news and the possibility that it can influence political, economic, and social well-being. To understand how false news spreads, Vosoughi et al. used a data set of rumor cascades on Twitter from 2006 to 2017. About 126,000 rumors were spread by ∼3 million people. False news reached more people than the truth; the top 1% of false news cascades diffused to between 1000 and 100,000 people, whereas the truth rarely diffused to more than 1000 people. Falsehood also diffused faster than the truth. The degree of novelty and the emotional reactions of recipients may be responsible for the differences observed. Science, this issue p. 1146 A large-scale analysis of tweets reveals that false rumors spread further and faster than the truth. We investigated the differential diffusion of all of the verified true and false news stories distributed on Twitter from 2006 to 2017. The data comprise ~126,000 stories tweeted by ~3 million people more than 4.5 million times. We classified news as true or false using information from six independent fact-checking organizations that exhibited 95 to 98% agreement on the classifications. Falsehood diffused significantly farther, faster, deeper, and more broadly than the truth in all categories of information, and the effects were more pronounced for false political news than for false news about terrorism, natural disasters, science, urban legends, or financial information. We found that false news was more novel than true news, which suggests that people were more likely to share novel information. Whereas false stories inspired fear, disgust, and surprise in replies, true stories inspired anticipation, sadness, joy, and trust. Contrary to conventional wisdom, robots accelerated the spread of true and false news at the same rate, implying that false news spreads more than the truth because humans, not robots, are more likely to spread it.

DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs

This paper describes our approach for the Detecting Stance in Tweets task (SemEval-2016 Task 6). We utilized recent advances in short text categorization using deep learning to create word-level and character-level models. The choice between word-level and character-level models in each particular case was informed through validation performance. Our final system is a combination of classifiers using word-level or character-level models. We also employed novel data augmentation techniques to expand and diversify our training dataset, thus making our system more robust. Our system achieved a macro-average precision, recall and F1-scores of 0.67, 0.61 and 0.635 respectively.

Rumor Gauge: Predicting the Veracity of Rumors on Twitter

The spread of malicious or accidental misinformation in social media, especially in time-sensitive situations, such as real-world emergencies, can have harmful effects on individuals and society. In this work, we developed models for automated verification of rumors (unverified information) that propagate through Twitter. To predict the veracity of rumors, we identified salient features of rumors by examining three aspects of information spread: linguistic style used to express rumors, characteristics of people involved in propagating information, and network propagation dynamics. The predicted veracity of a time series of these features extracted from a rumor (a collection of tweets) is generated using Hidden Markov Models. The verification algorithm was trained and tested on 209 rumors representing 938,806 tweets collected from real-world events, including the 2013 Boston Marathon bombings, the 2014 Ferguson unrest, and the 2014 Ebola epidemic, and many other rumors about various real-world events reported on popular websites that document public rumors. The algorithm was able to correctly predict the veracity of 75% of the rumors faster than any other public source, including journalists and law enforcement officials. The ability to track rumors and predict their outcomes may have practical applications for news consumers, financial markets, journalists, and emergency services, and more generally to help minimize the impact of false information on Twitter.

A Human-Machine Collaborative System for Identifying Rumors on Twitter

The spread of rumors on social media, especially in time-sensitive situations such as real-world emergencies, can have harmful effects on individuals and society. In this work, we developed a human-machine collaborative system on Twitter for fast identification of rumors about real-world events. The system reduces the amount of information that users have to sift through in order to identify rumors about real-world events by several orders of magnitude.

Improving automatic speech recognition through head pose driven visual grounding

In this paper, we present a multimodal speech recognition system for real world scene description tasks. Given a visual scene, the system dynamically biases its language model based on the content of the visual scene and visual attention of the speaker. Visual attention is used to focus on likely objects within the scene. Given a spoken description the system then uses the visually biased language model to process the speech. The system uses head pose as a proxy for the visual attention of the speaker. Readily available standard computer vision algorithms are used to recognize the objects in the scene and automatic real time head pose estimation is done using depth data captured via a Microsoft Kinect. The system was evaluated on multiple participants. Overall, incorporating visual information into the speech recognizer greatly improved speech recognition accuracy. The rapidly decreasing cost of 3D sensing technologies such as the Kinect allows systems with similar underlying principles to be used for many speech recognition tasks where there is visual information.

Twitter Demographic Classification Using Deep Multi-modal Multi-task Learning.

Twitter should be an ideal place to get a fresh read on how different issues are playing with the public, one that’s potentially more reflective of democracy in this new media age than traditional polls. Pollsters typically ask people a fixed set of questions, while in social media people use their own voices to speak about whatever is on their minds. However, the demographic distribution of users on Twitter is not representative of the general population. In this paper, we present a demographic classifier for gender, age, political orientation and location on Twitter. We collected and curated a robust Twitter demographic dataset for this task. Our classifier uses a deep multi-modal multi-task learning architecture to reach a state-of-the-art performance, achieving an F1-score of 0.89, 0.82, 0.86, and 0.68 for gender, age, political orientation, and location respectively.

Dense Home-Based Recordings Reveal Typical and Atypical Development of Tense/Aspect in a Child with Delayed Language Development.

Studies investigating the development of tense/aspect in children with developmental disorders have focused on production frequency and/or relied on short spontaneous speech samples. How children with developmental disorders use future forms/constructions is also unknown. The current study expands this literature by examining frequency, consistency, and productivity of past, present, and future usage, using the Speechome Recorder, which enables collection of dense, longitudinal audio-video recordings of childrens speech. Samples were collected longitudinally in a child who was previously diagnosed with autism spectrum disorder, but at the time of the study exhibited only language delay [Audrey], and a typically developing child [Cleo]. While Audrey was comparable to Cleo in frequency and productivity of tense/aspect use, she was atypical in her consistency and production of an unattested future form. Examining additional measures of densely collected speech samples may reveal subtle atypicalities that are missed when relying on only few typical measures of acquisition.

Human Atlas: A Tool for Mapping Social Networks

Most social network analyses focus on online social networks. While these networks encode important aspects of our lives they fail to capture many real-world social connections. Most of these connections are, in fact, public and known to the members of the community. Mapping them is a task very suitable for crowdsourcing: it is easily broken down in many simple and independent subtasks. Due to the nature of social networks-presence of highly connected nodes and tightly knit groups-if we allow users to map their immediate connections and the connections between them, we will need few participants to map most connections within a community. To this end, we built the Human Atlas, a web-based tool for mapping social networks. To test it, we partially mapped the social network of the MIT Media Lab. We ran a user study and invited members of the community to use the tool. In 4.6 man-hours, 22 participants mapped 984 connections within the lab, demonstrating the potential of the tool.

TweetVista: An AI-Powered Interactive Tool for Exploring Conversations on Twitter

We present TweetVista, an interactive web-based tool for mapping the conversation landscapes on Twitter. TweetVista is an intelligent and interactive desktop web application for exploring the conversation landscapes on Twitter. Given a dataset of tweets, the tool uses advanced NLP techniques using deep neural networks and a scalable clustering algorithm to map out coherent conversation clusters. The interactive visualization engine then enables the users to explore these clusters. We ran three case studies using datasets about the 2016 US presidential election and the summer 2016 Orlando shooting. Despite the enormous size of these datasets, using TweetVista users were able to quickly and clearly make sense of the various conversation topics around these datasets.