X4Impact Research Papers
Applied Research Papers and Social Insights Papers
This is a selection of our Applied Research Papers; they showcase the use of Artificial Intelligence – AI, under ethical principles, to address a social issue. We also generate Insights Papers, focused on gathering novel insights from Domain-Specific Knowledge Graphs created by our team and by the AI for the Public Interest Division of Giving Tech Labs, our parent company.
Domain-Specific Knowledge Graphs as a Public Service
Sponsored by Microsoft
This applied research paper explores the practical applications of Domain-Specific Knowledge Graphs that allow for the extraction of information from trusted published and unpublished sources, to map the extracted information to an ontology defined in collaboration with sector experts, and to enable the public to go from single queries into ongoing conversations meeting their knowledge needs reliably.
We focused on Social-Impact Funding, an area of need for over one million nonprofit organizations, foundations, government entities, social entrepreneurs, impact investors, and academic institutions in the US.
Published by KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningAugust 2020 Pages 2793–2801
Acoustic Measures for Real-Time Voice Coaching
sponsored by GIVING TECH LABS
Our voices can convey many different types of thoughts and intent. How we say things is as important as what we say.
This paper presents methodologies for computing a set of physical properties from sound waves of a speaker's voice directly, referred to as acoustic measures. While preserving 100% of the user's privacy. Based on our findings, a voice coaching app can guide users, in real-time, to modify their speech's auditory measures, such as rate of speech, energy level, and intonation, to achieve their intended communication goals.
Published by KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining August 2020 Pages 2755–2763
Limited Broadband Access as a Barrier to Economic Mobility of Older Americans
Sponsored by CWI Labs
This research provides insights about broadband related barriers that prevent older Americans 65+ from being an active part of the US workforce. Through applying machine learning and natural language processing methods, five important factors are surfaced that characterize the lack of broadband access as a barrier to the economic mobility of older Americans.
- Geography and Infrastructure
- Broadband Supply and it's Quality
- Affordability and Economic Factors
- Adoption and Awareness about the Broadband Benefits
- Support System and Policy
Economic Mobility, Voice, and Aging
sponsored by VULCAN
This applied research paper builds on a previously published research paper: Acoustic Measures for Real-Time Voice Coaching – Real-Time Voice Coach with 100% user privacy, published by KDD in August 2020.
As a next step, we explore how aging affects our ability to connect with others properly. We are focused on finding insights that could become a baseline for enabling the creation of tools to assist aging individuals in their economic mobility and professional development. Insights could also inform social programs to mitigate subconscious biases that arise from our communication styles.
For publication in Q1 2021
Economic Mobility of Older Workers in the U.S.
Sponsored by CWI Labs
Problem Context: Elevating Job Seekers 65+ in our National Discussion of Recovery and Economic Mobility.
Applied AI Research Paper: Domain Specific Knowledge Graph - DSKG, on the Economic Mobility of Older Workers in the U.S.
The DSKG created can be used to identify inefficiencies or gaps in legislation and policies, or to create a safe search engine for older workers to find resources to improve their economic mobility.
Initial Population Focus: 65+ Americans and their economic mobility needs addressed through workforce development, skills gap identification, systemic barriers to employment or entrepreneurship.
Target Q1 2021
Voice Barriers for Social Connections
sponsored by VULCAN
This applied research paper builds on a previously published research paper: Acoustic Measures for Real-Time Voice Coaching – Real-Time Voice Coach with 100% user privacy, published by KDD in August 2020. And also on our research paper on Voice and Aging submitted for Publication in Oct 2020.
As a next step, we explore how specific characteristics of our speech, which can be influenced by internal factors such as aging or external factors such as speaking a second language, negatively affect our ability to connect with others. Insights can inform social programs to mitigate biases that arise from our communication styles or from physical impediments that affect certain characteristics of our voices.
Targeting submission for publication in Q1 2021