Assessing Public Opinion on CRISPR-Cas9: Combining Crowdsourcing and Deep Learning

Marcel Salathé
JMIR PUBLICATIONS, INC, 2020
Journal paper

Abstract

Background: The discovery of the CRISPR-Cas9-based gene editing method has opened unprecedented new potential for biological and medical engineering, sparking a growing public debate on both the potential and dangers of CRISPR applications. Given the speed of technology development and the almost instantaneous global spread of news, it is important to follow evolving debates without much delay and in sufficient detail, as certain events may have a major long-term impact on public opinion and later influence policy decisions. Objective: Social media networks such as Twitter have shown to be major drivers of news dissemination and public discourse. They provide a vast amount of semistructured data in almost real-time and give direct access to the content of the conversations. We can now mine and analyze such data quickly because of recent developments in machine learning and natural language processing. Methods: Here, we used Bidirectional Encoder Representations from Transformers (BERT), an attention-based transformer model, in combination with statistical methods to analyze the entirety of all tweets ever published on CRISPR since the publication of the first gene editing application in 2013. Results: We show that the mean sentiment of tweets was initially very positive, but began to decrease over time, and that this decline was driven by rare peaks of strong negative sentiments. Due to the high temporal resolution of the data, we were able to associate these peaks with specific events and to observe how trending topics changed over time. Conclusions: Overall, this type of analysis can provide valuable and complementary insights into ongoing public debates, extending the traditional empirical bioethics toolset.

Official source

https://infoscience.epfl.ch/record/281099?ln=en

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts

Related publications

Marcel Salathé
JMIR PUBLICATIONS, INC, 2020
Journal paper

Abstract

Official source

https://infoscience.epfl.ch/record/281099?ln=en

About this result

Related concepts (15)

Related concepts

Related publications (8)

Related publications

Related publications (8)

The quantification of population-level health behaviors is crucial for guiding public health policy. However, traditional methods for measuring such health behaviors have several short- comings. In recent years social media data has been successfully used to measure health behaviors and may be used as a low-cost and real-time addition to traditional data sources. Methods from the field of natural language processing are increasingly used to automatically process, filter and categorize the rapidly growing amount of publicly available social media data. However, a number of methodological challenges limit the rate at which we can generate insight from such data. In this work I will argue that long-term investment into digital infrastructure and open source tooling is required in order to overcome these challenges. In chapter 2 we introduce the Crowd- breaks platform which is the basis of this thesis. Crowdbreaks is an open source framework for real-time data collection, continuous crowdsourced annotation, and continuous re-training of machine learning classifiers. In contrast to traditional research workflows, projects on Crowdbreaks run over an extended period of time, allowing for the observation of health trends over multiple years while keeping algorithms up-to-date. In chapter 3 we quantify the occurrence of concept drift in vaccine-related Twitter data, which further validates the need for the Crowdbreaks platform. In chapter 4 we use the Crowdbreaks platform to trace sentiment towards the novel gene-editing technology CRISPR/Cas9 back to its first application in 2013 and investigate how public opinion may have been affected in context of recent scandals sur- rounding the technology. In chapter 5 we turn our attention to the COVID-19 pandemic and analyze who was speaking and who was heard in the early months of the pandemic. Chapter 6 builds on this work and explores the dynamics of Twitter communities during the COVID-19 pandemic. Lastly, in chapter 7 we introduce COVID-Twitter-BERT, a domain-specific language model which has been used in various downstream natural language processing applications on COVID-19-related Twitter data.

EPFL2021

Motion models for robust 3D human body tracking

Raquel Urtasun

In this work, we propose new ways to learn pose and motion priors models and show that they can be used to increase the performance of 3D body tracking algorithms, resulting in very realistic motions under very challenging conditions. We first explored an approach to 3D people tracking that combines learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable criterion whose differential structure is rich enough for optimization to be accomplished via hill-climbing. This avoids the computational expense of Monte Carlo methods, while yielding very good results under challenging conditions. To demonstrate the generality of the approach we show that we can learn and track cyclic motions such as walking and running, as well as acyclic motions such as a golf swing. We also show results from both monocular and multi-camera tracking. Finally, we provide results with a motion model learned from multiple activities, and show how these models can be used for recognition and motion generation. The major limitation of these linear motion models is that they required many noiseless, segmented and time warped examples to create a complete database with good generalization properties. We therefore investigated more complex non-linear statistical techniques. We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose. The SGPLVM simultaneously optimizes a low-dimensional embedding of the high-dimensional pose data and a density function that both gives higher probability to points close to training data and provides a nonlinear probabilistic mapping from the low-dimensional latent space to the full-dimensional pose space. The SGPLVM is a natural choice when only small amounts of training data are available. We demonstrate our approach with two distinct motions, golfing and walking. We show that the SGPLVM sufficiently constrains the problem such that tracking can be accomplished with straightforward deterministic optimization. However, in the presence of very noisy or missing data, for example due to occlusions, the simplistic second order Markov model we use is not realistic enough to sufficiently constrain the algorithm. Moreover, when learning models that contain stylistic diversity, from different people or from the same person performing an activity multiple times, the SGPLVM results in models whose latent trajectories are not smooth, and are therefore not suited for hill climbing tracking. Finally, we present a more powerfull approach based on the Gaussian Process Dynamical Models (GPDMs) that combines the strengths of the two previous ones. We advocate the use of GPDMs for learning human pose and motion priors. A GPDM provides a low-dimensional embedding of human motion data, with a density function that gives higher probability to poses and motions close to the training data. With Bayesian model averaging a GPDM can be learned from relatively small amounts of data, and it generalizes gracefully to motions outside the training set. Here we modify the GPDM to permit learning from motions with significant stylistic variation. The resulting priors are effective for tracking a range of human walking styles, despite weak and noisy image measurements and significant occlusions.

EPFL2006

Machine Vision-Based Analysis of Gaze and Visual Context

Basilio Noris

Visual behavior, and specifically gaze directed at objects and people, is a fundamental cue for understanding how children with Autism Spectrum Disorder (ASD) experience and respond to social interaction. Indeed atypical behaviors such as averting the gaze from faces, looking out of the corner of the eyes, and having difficulties disengaging from non-social stimuli, are well known symptoms of this developmental disorder. However, studying these atypicalities presents several technical challenges, both at a hardware and software level. Traditionally this type of analysis is done by viewing video recordings of the child's interaction and manually rating gaze behavior episodes. This data collection procedure is often a time consuming process, and all the results have to be checked by multiple raters to ensure reliability. When automated systems are used, issues of intrusiveness, robustness and reliability have to be taken into consideration, and their impact on the behavior of the child needs to be accounted for. Moreover, children often do not cooperate to the same extent as an adult participant in the experimental process. This thesis addresses the problem of studying the visual behavior of children during dyadic interactions, using tools from machine learning and computer vision. One focus is on the technical aspects of how to measure the direction of the gaze, and how to recognize what the child is looking at. Another is on the development of semi-automated data analysis collection methods that can be efficiently checked and corrected by the experimenter. The concrete contribution of this work is a set of algorithms and software tools that allow firstly the measurement of multiple gaze factors and the quantification of attentional episodes to objects and people, and secondly the analysis of their distributions, extrema, and spatio-temporal correlations. These tools are applied to the specific case of children affected by ASD, which allows the assessment of how their gaze strategies differ from typically developing children. To measure the direction of the gaze of children in a robust and unobtrusive way, the main recording tool employed is the WearCam: a head-mounted camera developed in our laboratory, that records the eyes of the child and an image of the broad field of view. The reflected images of the eyes are mapped to the coordinates of the gaze in the field of view by means of data-driven appearance-based methods. This is a different approach to the standard methods for gaze tracking, as it makes no use of active lighting, and allows the gathering of data to be postponed until after the recording. This is especially useful as it relieves the children from actively participating in a calibration phase. The task of identifying at which object or person the child is looking is approached through a semi-automated analysis of the recordings. A computationally intensive face and object detection system provides a preliminary estimation, while a faster on-line method can be used by the experimenter to correct that estimation by providing active cues. Furthermore, to allow faster processing of the recordings, a set of features specific to the relevant objects is extracted. The combination of these approaches greatly reduces the time needed to collect the data, while ensuring that reliable data is obtained. The development of these tools facilitates the studying of the behavior of children during natural interactions with an adult. Our approach is able to obtain information on several gaze factors, such as the frequency and length of fixations to faces, how extensively the gaze explores the broad field of view and the use of central vs. peripheral vision. The experimental observations obtained from the comparison of 29 children with autism to 29 typically developing children provide, in two separate studies, quantitative measurements in support of known deficits, such as reduced gaze to faces, downcast gaze and shorter fixations to social stimuli; deficits that were so far documented only in a qualitative manner. More importantly, the results highlight a novel hypothesis, not yet documented, suggesting that ASD children may use a strategy of continuous peripheral viewing to overcome their visual processing difficulties. These observations thus provide an experimental contribution to clinical research in autism.

EPFL2011