skip to main content


Title: From Crowd Ratings to Predictive Models of Newsworthiness to Support Science Journalism
The scale of scientific publishing continues to grow, creating overload on science journalists who are inundated with choices for what would be most interesting, important, and newsworthy to cover in their reporting. Our work addresses this problem by considering the viability of creating a predictive model of newsworthiness of scientific articles that is trained using crowdsourced evaluations of newsworthiness. We proceed by first evaluating the potential of crowd-sourced evaluations of newsworthiness by assessing their alignment with expert ratings of newsworthiness, analyzing both quantitative correlations and qualitative rating rationale to understand limitations. We then demonstrate and evaluate a predictive model trained on these crowd ratings together with arXiv article metadata, text, and other computed features. Based on the crowdsourcing protocol we developed, we find that while crowdsourced ratings of newsworthiness often align moderately with expert ratings, there are also notable differences and divergences which limit the approach. Yet despite these limitations we also find that the predictive model we built provides a reasonably precise set of rankings when validated against expert evaluations (P@10 = 0.8, P@15 = 0.67), suggesting that a viable signal can be learned from crowdsourced evaluations of newsworthiness. Based on these findings we discuss opportunities for future work to leverage crowdsourcing and predictive approaches to support journalistic work in discovering and filtering newsworthy information.  more » « less
Award ID(s):
1845460
NSF-PAR ID:
10386489
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Proceedings of the ACM on Human-Computer Interaction
Volume:
6
Issue:
CSCW2
ISSN:
2573-0142
Page Range / eLocation ID:
1 to 28
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Wetland loss is increasing rapidly, and there are gaps in public awareness of the problem. By crowdsourcing image analysis of wetland morphology, academic and government studies could be supplemented and accelerated while engaging and educating the public. The Land Loss Lookout (LLL) project crowdsourced mapping of wetland morphology associated with wetland loss and restoration. We demonstrate that volunteers can be trained relatively easily online to identify characteristic wetland morphologies, or patterns present on the landscape that suggest a specific geomorphological process. Results from a case study in coastal Louisiana revealed strong agreement among nonexpert and expert assessments who agreed on classifications at least 83% and at most 94% of the time. Participants self‐reported increased knowledge of wetland loss after participating in the project. Crowd‐identified morphologies are consistent with expectations, although more work is needed to directly compare LLL results with previous studies. This work provides a foundation for using crowd‐based wetland loss analysis to increase public awareness of the issue, and to contribute to land surveys or train machine learning algorithms.

     
    more » « less
  2. As AI-based face recognition technologies are increasingly adopted for high-stakes applications like locating suspected criminals, public concerns about the accuracy of these technologies have grown as well. These technologies often present a human expert with a shortlist of high-confidence candidate faces from which the expert must select correct match(es) while avoiding false positives, which we term the “last-mile problem.” We propose Second Opinion, a web-based software tool that employs a novel crowdsourcing workflow inspired by cognitive psychology, seed-gather-analyze, to assist experts in solving the last-mile problem. We evaluated Second Opinion with a mixed-methods lab study involving 10 experts and 300 crowd workers who collaborate to identify people in historical photos. We found that crowds can eliminate 75% of false positives from the highest-confidence candidates suggested by face recognition, and that experts were enthusiastic about using Second Opinion in their work. We also discuss broader implications for crowd–AI interaction and crowdsourced person identification. 
    more » « less
  3. null (Ed.)
    Crowdsourcing is widely used to create data for common natural language understanding tasks. Despite the importance of these datasets for measuring and refining model understanding of language, there has been little focus on the crowdsourcing methods used for collecting the datasets. In this paper, we compare the efficacy of interventions that have been proposed in prior work as ways of improving data quality. We use multiple-choice question answering as a testbed and run a randomized trial by assigning crowdworkers to write questions under one of four different data collection protocols. We find that asking workers to write explanations for their examples is an ineffective stand-alone strategy for boosting NLU example difficulty. However, we find that training crowdworkers, and then using an iterative process of collecting data, sending feedback, and qualifying workers based on expert judgments is an effective means of collecting challenging data. But using crowdsourced, instead of expert judgments, to qualify workers and send feedback does not prove to be effective. We observe that the data from the iterative protocol with expert assessments is more challenging by several measures. Notably, the human--model gap on the unanimous agreement portion of this data is, on average, twice as large as the gap for the baseline protocol data. 
    more » « less
  4. null (Ed.)
    The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge. 
    more » « less
  5. Abstract Research Summary

    Theories of crowdsourced search suggest that firms should limit the search space from which solutions to the problem may be drawn by constraining the problem definition. In turn, problems that are not or cannot be constrained should be tackled through other means of innovation. We propose that unconstrained problems can be crowdsourced, but firms need to govern the crowds differently. Specifically, we hypothesize that firms should govern crowds for solving unconstrained problems by instructing them not just to solve the problem but also to help (re)define the problem by offering their problem frames and integrating others' frames. We find evidence for this interaction hypothesis in a field study of over a thousand participants in 20 different crowdsourcing events with interventions for the different governance approaches.

    Managerial Summary

    Unconstrained innovation problems, which require finding a new product and a new market at the same time, are thought to be difficult to solve via crowdsourcing. We propose and test a governance approach for problem‐finding, that is, (re)defining the firm's original problem statement by instructing crowds to make their problem frames explicit (by posting them) and to integrate others’ problem frames into their solution ideas. In doing so, we provide guidance for firms hoping to use crowdsourcing for both unconstrained and constrained problems. For constrained problems, as widely known, firms should govern for problem‐solving only; for unconstrained problems, they should govern for problem‐finding and problem‐solving. Both forms of governance are “light‐touch,” requiring only minimal intervention in the form of instructions for the crowd at the beginning of the crowdsourcing event.

     
    more » « less