2023:Program/Technology/3LZNNM-Improving Content Quality with ORES: A Demonstration of the Objective Revision Evaluation Service Tool

The following is a mirror of what are publicly available details of submission made at the call for proposal platform, Pretalx. Any changes here may be overwritten by a bot while syncing updates from Pretalx (3LZNNM). Changes are monitored and may be updated into Pretalx if they do not change the context of the submission (i.e. correcting typographical errors).

Title: Improving Content Quality with ORES: A Demonstration of the Objective Revision Evaluation Service Tool

Speakers:

Joris Darlington Quarshie

Joris Darlington Quarshie is an experienced Data Scientist, Developer Advocate, and Wikimedia Tech Community Builder. He is the catalyst that brings your brand, stakeholders, data, technology and decisions together to build and deliver better products, and create delightful customer experiences, resulting in accelerated💰 growth 📈 and impact. He is a key advocate and promoter of Sustainable Development Goal 4: Promoting data science education for all. Helping bridge the technology skills gap for the underserved talents in Africa and globally is his top priority agenda. He has developed initiatives and tailored programs that drive greater inclusion and diversity in the data science, software engineering and other technological fields through providing free tech educational and professional opportunities to over 9,000+ highly deserving Africans and the black community at large. Tech communities in Ghana and Africa at large🏅 have feted Joris for his advocacy efforts and contributions to increasing the participation, inclusivity, representation and diversity of black people in the technological field, and creating robust pipelines of qualified, trained and talented tech professionals.

Pretalx link

Etherpad link

Room: Room 309

Start time: Thu, 17 Aug 2023 11:15:00 +0800

End time: Thu, 17 Aug 2023 11:55:00 +0800

Type: No (pretalx) session type id specified

Track: Technology

Submission state: confirmed

Duration: 40 minutes

Do not record: false

Presentation language: en

Abstract & description

Abstract

Objective Revision Evaluation Service(ORES) is a powerful tool that uses machine learning algorithms to evaluate the quality and reliability of the content on Wikipedia. ORES helps identify potential vandalism, bias, and inaccuracies in articles, empowering editors to make more informed decisions about which articles need attention. In this demonstration, we will showcase the features and benefits of ORES, including how it can improve the overall quality of Wikipedia articles.

Description

In this 1 hour demonstration, we will briefly provide an overview of the Objective Revision Evaluation Service (ORES) tool and its key features. We will demonstrate how ORES analyzes articles for potential issues and generates scores that help editors prioritize their work. We will also discuss the various machine learning models ORES uses to evaluate the content, including classifiers for detecting vandalism, identifying good faith edits, and detecting article quality.

We will provide practical examples of how editors can use ORES to streamline their workflows and identify articles that need attention. We will also discuss the benefits of ORES for new editors, who may be overwhelmed by the volume of content on Wikipedia and need guidance on where to focus their efforts.

Finally, we will showcase how ORES can be used to support community-driven initiatives, such as WikiProjects, that aim to improve the quality of specific topic areas on Wikipedia. We will demonstrate how ORES can help identify articles that need attention within a particular topic area and provide insights into the types of issues that editors may need to address.

Further details

Qn. How does your session relate to the event themes: Diversity, Collaboration Future?

The demonstration of the Objective Revision Evaluation Service (ORES) tool relates to the event themes of Diversity, Collaboration, and Future in several ways:

Diversity: The ORES tool can help to support diversity on Wikipedia by providing automated tools for identifying problematic content and supporting content review processes. By improving the quality of content on Wikipedia, the tool can help to create a more inclusive and diverse encyclopedia.

Collaboration: The ORES tool is designed to support collaboration among editors on Wikipedia by providing a common set of metrics for assessing the quality and trustworthiness of the content. This can help to promote collaboration by providing editors with a shared understanding of the quality of content and prioritizing work that needs to be done.

Future: The ORES tool is an example of how machine learning and AI can be used to support the work of editors on Wikipedia. As these technologies continue to evolve, they have the potential to transform the way that knowledge is created and shared and to create a more sustainable future for online collaboration and content creation.

In Conclusion, the ORES tool demonstration aligns with the event themes of Diversity, Collaboration, and Future by showcasing a tool that can help to improve the quality of content on Wikipedia, promote collaboration among editors, and support the continued growth and evolution of the world’s largest collaborative knowledge project.

Qn. What is the experience level needed for the audience for your session?

Average knowledge about Wikimedia projects or activities

Qn. What is the most appropriate format for this session?

• Onsite in Singapore
• Remote online participation, livestreamed
• Remote from a satellite event
• Hybrid with some participants in Singapore and others dialing in remotely
• Pre-recorded and available on demand