class: center, middle, inverse, title-slide #
Data Science for Social Good
Women Who Code Berlin
###
Lisa Hehnke
dataplanes.org |
@DataPlanes
###
July 24, 2019
--- class: center, middle ## <font size='7'>"The job of the data scientist is to ask the right questions."</font> <br> <font size='5'>Hilary Mason <br> (Data scientist & founder of Fast Forward Labs)</font> <img src="images/hilary-mason.png" width="250px" style="display: block; margin: auto;" /> ??? Image credit: [Story in a Bottle](http://storyinabottle.charmingrobot.com/2016/02/10/hilary-mason/) --- class: inverse, center, middle # What data science usually looks like... --- ## Image recognition <img src="images/pug-image.png" width="2585" style="display: block; margin: auto;" /> ??? Image credit: [Pinterest](https://www.pinterest.com/pin/597571444276861714/) --- ## Recommender systems <img src="images/youtube-recommender.png" width="2401" style="display: block; margin: auto;" /> --- class: center, middle ## <font size='9'>But there's more to it than that. We need to democratize the potential of data science.</font> --- <img src="images/zuckerberg-idea.png" width="1321" style="display: block; margin: auto;" /> --- class: inverse, center, middle # Data science for good <br> <font size='6'>(a.k.a. asking the right kind of questions)</font> --- ## Knowing your <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 384 512"><path d="M202.021 0C122.202 0 70.503 32.703 29.914 91.026c-7.363 10.58-5.093 25.086 5.178 32.874l43.138 32.709c10.373 7.865 25.132 6.026 33.253-4.148 25.049-31.381 43.63-49.449 82.757-49.449 30.764 0 68.816 19.799 68.816 49.631 0 22.552-18.617 34.134-48.993 51.164-35.423 19.86-82.299 44.576-82.299 106.405V320c0 13.255 10.745 24 24 24h72.471c13.255 0 24-10.745 24-24v-5.773c0-42.86 125.268-44.645 125.268-160.627C377.504 66.256 286.902 0 202.021 0zM192 373.459c-38.196 0-69.271 31.075-69.271 69.271 0 38.195 31.075 69.27 69.271 69.27s69.271-31.075 69.271-69.271-31.075-69.27-69.271-69.27z"/></svg><svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 384 512"><path d="M202.021 0C122.202 0 70.503 32.703 29.914 91.026c-7.363 10.58-5.093 25.086 5.178 32.874l43.138 32.709c10.373 7.865 25.132 6.026 33.253-4.148 25.049-31.381 43.63-49.449 82.757-49.449 30.764 0 68.816 19.799 68.816 49.631 0 22.552-18.617 34.134-48.993 51.164-35.423 19.86-82.299 44.576-82.299 106.405V320c0 13.255 10.745 24 24 24h72.471c13.255 0 24-10.745 24-24v-5.773c0-42.86 125.268-44.645 125.268-160.627C377.504 66.256 286.902 0 202.021 0zM192 373.459c-38.196 0-69.271 31.075-69.271 69.271 0 38.195 31.075 69.27 69.271 69.27s69.271-31.075 69.271-69.271-31.075-69.27-69.271-69.27z"/></svg> Using data science for social good requires <b>impact-based projects</b> that are built on <b>adequate data</b>. But above all, we need the <b>expertise of social data scientists</b> who ask the following questions: -- 1. What impact do we want to have with our project? What is the target group? -- 2. What are the challenges and needs of the target group? -- 3. What kind of data is available and how can we access it? -- 4. What should our final product look like? How can we implement it technically? -- 5. Who uses the final product? How often? Which criteria must the product meet to truly add value? -- 6. And last, but certainly not least: What could potentially go wrong? 💥 --- class: inverse, center, middle # Harnessing the potential of data science --- ## [DataKind](https://www.datakind.org/): Home fire risk map .pull-left[ - <b>Context:</b> The Home Fire Campaign by the American Red Cross aims to reduce the number of deaths and injuries caused by home fires - <b>Objective:</b> Identify high-risk neighborhoods to target for in-home fire safety education and free smoke alarms - <b>Approach:</b> Use ML techniques that leverage data from multiple sources to predict aggregate neighborhood home fire risk ] .pull-right[  ] .center[ <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 576 512"><path d="M488 312.7V456c0 13.3-10.7 24-24 24H348c-6.6 0-12-5.4-12-12V356c0-6.6-5.4-12-12-12h-72c-6.6 0-12 5.4-12 12v112c0 6.6-5.4 12-12 12H112c-13.3 0-24-10.7-24-24V312.7c0-3.6 1.6-7 4.4-9.3l188-154.8c4.4-3.6 10.8-3.6 15.3 0l188 154.8c2.7 2.3 4.3 5.7 4.3 9.3zm83.6-60.9L488 182.9V44.4c0-6.6-5.4-12-12-12h-56c-6.6 0-12 5.4-12 12V117l-89.5-73.7c-17.7-14.6-43.3-14.6-61 0L4.4 251.8c-5.1 4.2-5.8 11.8-1.6 16.9l25.5 31c4.2 5.1 11.8 5.8 16.9 1.6l235.2-193.7c4.4-3.6 10.8-3.6 15.3 0l235.2 193.7c5.1 4.2 12.7 3.5 16.9-1.6l25.5-31c4.2-5.2 3.4-12.7-1.7-16.9z"/></svg> datakind.org <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 512 512"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"/></svg> @DataKind <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 448 512"><path d="M448 56.7v398.5c0 13.7-11.1 24.7-24.7 24.7H309.1V306.5h58.2l8.7-67.6h-67v-43.2c0-19.6 5.4-32.9 33.5-32.9h35.8v-60.5c-6.2-.8-27.4-2.7-52.2-2.7-51.6 0-87 31.5-87 89.4v49.9h-58.4v67.6h58.4V480H24.7C11.1 480 0 468.9 0 455.3V56.7C0 43.1 11.1 32 24.7 32h398.5c13.7 0 24.8 11.1 24.8 24.7z"/></svg> DataKindOrg ] ??? Link: [Home Fire Risk Map](https://home-fire-risk.github.io/smoke_alarm_map/) --- ## [CorrelAid](https://correlaid.org/): Online movements .pull-left[ - <b>Context:</b> Social activist Ali Can launched the two hashtags #MeTwo and #We2 to draw attention to racial discrimination and multi-faceted racial identities - <b>Objective:</b> Evaluate the content, key actors, and temporal dynamics of the Twitter campaigns to assess their potential and limitations - <b>Approach:</b> Use NLP techniques and social network analysis to identify important topics and influential actors ] .pull-right[  ] .center[ <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 576 512"><path d="M488 312.7V456c0 13.3-10.7 24-24 24H348c-6.6 0-12-5.4-12-12V356c0-6.6-5.4-12-12-12h-72c-6.6 0-12 5.4-12 12v112c0 6.6-5.4 12-12 12H112c-13.3 0-24-10.7-24-24V312.7c0-3.6 1.6-7 4.4-9.3l188-154.8c4.4-3.6 10.8-3.6 15.3 0l188 154.8c2.7 2.3 4.3 5.7 4.3 9.3zm83.6-60.9L488 182.9V44.4c0-6.6-5.4-12-12-12h-56c-6.6 0-12 5.4-12 12V117l-89.5-73.7c-17.7-14.6-43.3-14.6-61 0L4.4 251.8c-5.1 4.2-5.8 11.8-1.6 16.9l25.5 31c4.2 5.1 11.8 5.8 16.9 1.6l235.2-193.7c4.4-3.6 10.8-3.6 15.3 0l235.2 193.7c5.1 4.2 12.7 3.5 16.9-1.6l25.5-31c4.2-5.2 3.4-12.7-1.7-16.9z"/></svg> correlaid.org <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 512 512"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"/></svg> @CorrelAid <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 448 512"><path d="M448 56.7v398.5c0 13.7-11.1 24.7-24.7 24.7H309.1V306.5h58.2l8.7-67.6h-67v-43.2c0-19.6 5.4-32.9 33.5-32.9h35.8v-60.5c-6.2-.8-27.4-2.7-52.2-2.7-51.6 0-87 31.5-87 89.4v49.9h-58.4v67.6h58.4V480H24.7C11.1 480 0 468.9 0 455.3V56.7C0 43.1 11.1 32 24.7 32h398.5c13.7 0 24.8 11.1 24.8 24.7z"/></svg> WeAreCorrelAid ] --- ## [DSSG Berlin](https://dssg-berlin.org/): SchulePlus .pull-left[ - <b>Context:</b> SchulePlus matches high school students with internships to help them figure out their professional future - <b>Objective:</b> Understand the supply and demand for internships in the different states of Germany - <b>Approach:</b> Correlate searches for internships with the job posts in the internship database ] .pull-right[  ] .center[ <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 576 512"><path d="M488 312.7V456c0 13.3-10.7 24-24 24H348c-6.6 0-12-5.4-12-12V356c0-6.6-5.4-12-12-12h-72c-6.6 0-12 5.4-12 12v112c0 6.6-5.4 12-12 12H112c-13.3 0-24-10.7-24-24V312.7c0-3.6 1.6-7 4.4-9.3l188-154.8c4.4-3.6 10.8-3.6 15.3 0l188 154.8c2.7 2.3 4.3 5.7 4.3 9.3zm83.6-60.9L488 182.9V44.4c0-6.6-5.4-12-12-12h-56c-6.6 0-12 5.4-12 12V117l-89.5-73.7c-17.7-14.6-43.3-14.6-61 0L4.4 251.8c-5.1 4.2-5.8 11.8-1.6 16.9l25.5 31c4.2 5.1 11.8 5.8 16.9 1.6l235.2-193.7c4.4-3.6 10.8-3.6 15.3 0l235.2 193.7c5.1 4.2 12.7 3.5 16.9-1.6l25.5-31c4.2-5.2 3.4-12.7-1.7-16.9z"/></svg> dssg-berlin.org <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 512 512"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"/></svg> @dssgber ] --- ## [Lecturers without Borders](https://scied.network/): Networks .pull-left[ - <b>Context:</b> Lecturers without borders connects educational networks and scientists who use their travel opportunities to give free lectures to local students in developing countries - <b>Objective:</b> Analyze how social initiatives are working together in different parts of the world - <b>Approach:</b> Build database of schools which can host scientists ] .pull-right[  ] .center[ <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 576 512"><path d="M488 312.7V456c0 13.3-10.7 24-24 24H348c-6.6 0-12-5.4-12-12V356c0-6.6-5.4-12-12-12h-72c-6.6 0-12 5.4-12 12v112c0 6.6-5.4 12-12 12H112c-13.3 0-24-10.7-24-24V312.7c0-3.6 1.6-7 4.4-9.3l188-154.8c4.4-3.6 10.8-3.6 15.3 0l188 154.8c2.7 2.3 4.3 5.7 4.3 9.3zm83.6-60.9L488 182.9V44.4c0-6.6-5.4-12-12-12h-56c-6.6 0-12 5.4-12 12V117l-89.5-73.7c-17.7-14.6-43.3-14.6-61 0L4.4 251.8c-5.1 4.2-5.8 11.8-1.6 16.9l25.5 31c4.2 5.1 11.8 5.8 16.9 1.6l235.2-193.7c4.4-3.6 10.8-3.6 15.3 0l235.2 193.7c5.1 4.2 12.7 3.5 16.9-1.6l25.5-31c4.2-5.2 3.4-12.7-1.7-16.9z"/></svg> scied.network <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 512 512"><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"/></svg> @NetworkScied <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 448 512"><path d="M448 56.7v398.5c0 13.7-11.1 24.7-24.7 24.7H309.1V306.5h58.2l8.7-67.6h-67v-43.2c0-19.6 5.4-32.9 33.5-32.9h35.8v-60.5c-6.2-.8-27.4-2.7-52.2-2.7-51.6 0-87 31.5-87 89.4v49.9h-58.4v67.6h58.4V480H24.7C11.1 480 0 468.9 0 455.3V56.7C0 43.1 11.1 32 24.7 32h398.5c13.7 0 24.8 11.1 24.8 24.7z"/></svg> Lecturerswithoutborders ] --- ## Want to become more social? .pull-left[ <img src="images/correlaid-logo.png" width="9469" style="display: block; margin: auto;" /> ] .pull-right[ <img src="images/dssg-logo.svg" height="400px" style="display: block; margin: auto;" /> ] --- class: center, middle # Thanks! Slides made with <svg style="height:0.8em;top:.04em;position:relative;fill:#2c3e50e;" viewBox="0 0 512 512"><path d="M462.3 62.6C407.5 15.9 326 24.3 275.7 76.2L256 96.5l-19.7-20.3C186.1 24.3 104.5 15.9 49.7 62.6c-62.8 53.6-66.1 149.8-9.9 207.9l193.5 199.8c12.5 12.9 32.8 12.9 45.3 0l193.5-199.8c56.3-58.1 53-154.3-9.8-207.9z"/></svg> and R [*xaringan*](https://github.com/yihui/xaringan). Use cases by <b>[DataKind](https://www.datakind.org/)</b>, <b>[CorrelAid](https://correlaid.org/)</b>, <b>[DSSG Berlin](https://dssg-berlin.org/)</b>,<br> and <b>[Lecturers without Borders](https://sites.google.com/view/fellowshipresultsliubov/research-projects/lecturers-without-borders-researchers-mobility)</b>.