Happy new year! The UN has declared 2019 as the Year of Indigenous Languages, and will kick it off tomorrow on February 1. It may seem like a small thing, but by one estimate an indigenous language disappears every 14 days. And entire language, gone every 2 weeks! When the world loses a language, not only do those who speak it lose their mother tongue, but all of us lose potentially vital local knowledge of how to combat environmental threats. We also lose another piece of the diversity that makes our earth rich and vibrant. Saving indigenous languages isn’t just a nice pet project, it’s one that can make a huge difference to all of us, no matter what language we speak. Our January changemaker, Dr. Gregory D. S. Anderson, has been working to save indigenous languages for over a decade.
Dr. Anderson founded Living Tongues, a nonprofit organization dedicated to the documentation, revitalization, and maintenance of endangered languages, in 2005. Through the partnership between Living Tongues and National Geographic’s Enduring Voices project, Anderson traveled to places like Central Siberia, Bolivia and even Northern California to study, collect, and save indigenous languages. With Dr. K. David Harrison, Anderson developed a new way of looking at languages, identifying “language hotspots” around the globe. These are areas urgently in need of action to save languages.
Through Living Tongues, he has created over 100 talking dictionaries, created digital skills workshops and language technology kits in over a dozen countries, and worked tirelessly to document languages on 5 continents. No matter the language we use to say it, we owe Dr. Anderson a huge “thank you” for his work to save indigenous languages and the important knowledge the represent.
We started off the new year in a great way — by welcoming the fantastic Lauren Golanty to Public Good! Lauren joins us as our Director of Brand Partnerships. As we continue to grow and bring on more partners to do more good, Lauren will be responsible for client success and business development with corporate and non-profit clients.
Lauren’s extensive experience in client relations includes stints in financial services, executive search, legal and not-for-profit organizations. Most recently she spent five years with Riveron, where she grew relationships in the Midwest and lead marketing and public relations efforts nationally. She’s held similar roles at places like Houlihan Lokey (investment banking), Heidrick & Struggles (executive search), venture capital, and legal firms. Translation: she really knows her stuff!
But she’s not ALL business — Lauren’s also very active in her community through volunteering. She serves on the board of directors for Green City Market, and helped found Pilot Light Chefs, a group seeking to introduce food education as a standard component of the Chicago Public School curriculum. She’s also helping us discover some great new podcasts to dive into, and recommending the best menu items at Giant, her favorite place to eat in Chicago.
“I’m excited to join Public Good,” Lauren says. “What we’re doing allows people to make a positive impact on the world in a totally new way, and I want to extend that impact to as many people as possible.” She tells us that her favorite piece of advice has been “Don’t let Great be the opposite of Good,” the mantra of her last boss. It’s the perfect motto for us as we move forward into 2019 with Lauren on the team — doing great things by doing good!
Happy 2019! With a new year comes a new focus for Public Good that we’re excited to share with you. Since we launched our platform for nonprofits we’ve gotten to know so many mission-driven organizations doing great things in the world that inspire us daily. And we’ve grown a lot, too! A relatively simple fundraising platform has evolved into an action platform that allows people to make a difference in multiple ways on the issues important to them.
The capabilities of the platform and the potential to reach so many people to do more good make it an ideal tool for organizations who want to make a difference. This year we’ll focus on expanding and refining those capabilities. We’ll continue to partner with leading national and global news outlets like CNN and USA Today to tackle issues like impaired driving, natural disasters, and disease. We’ll continue to use our breakthrough machine learning and matching algorithm to give readers meaningful actions for the particular story they’re reading. And now through partnerships with large nonprofits like the Arbor Day Foundation, as well as other mission-driven brands and companies like Unilever, our innovative impact units will give readers even more ways to act on issues at the moment they’re inspired to do so.
But wait, there’s more! With our new focus comes a new website, too! Now publicgood.com better reflects our mission to make the news actionable, with information on how Public Good works with the media, nonprofits, and brands to make a difference on important issues. You’ll find everything from our whitepaper “Doing Well by Doing Good” to examples in the news to how you can get started. Take a look around and let us know what you think!
We’re thrilled to start 2019 with a renewed focus on our mission to make a difference, and we’re thankful you’re on the journey with us. We hope you’re renewed and refreshed and ready to make a difference in 2019 too!
This season we celebrate holidays from many different religions. The rich diversity of these beliefs adds valuable perspectives to our conversations and to our government. In honor of this diversity of cultures and religions, we honor the first Indian-American and first Sikh member of Congress, Dalip Singh Saund, as our December Changemaker.
Saung was born in 1899 in the Punjab province of India, and immigrated to the United States to attend graduate school at the University of California, Berkeley. There he studied farming (and mathematics) and stayed in the U.S. to become a farmer in southern California. He wrote in his autobiography “My guideposts were two of the most beloved men in history, Abraham Lincoln and Mahatma Gandhi” Like these idols, Saung advocated for equality and independence in speeches and in his writings. He was very active and involved in politics, campaigning for candidates and attending political meetings, but in 1923 the Supreme Court had ruled that ruled that immigrants from India were not eligible for U.S. citizenship, and so despite his passion for politics, Saund couldn’t even vote. He decided to change that.
Saund helped found the India Association of America and was elected its first president in 1942. Along with this new organization to gather the power of Indian Americans, Saund began his tireless work to secure the rights for Indian Americans and allow them to become citizens. He and other Indian Americans were able to convince Republican Clare Booth Luce and Democrat Emmanuel Celler to introduce a bill in Congress allowing citizenship to Indian Americans. But it was an uphill battle to get the bill passed. When a friend discouraged him from the battle, saying it was almost impossible that the United States would pass such a law, Saund responded “I have faith in the American sense of justice and fair play.”
Finally, after fighting racism (the original Supreme Court ruling was based on the idea that although Indians were considered “Caucasian,” they were not “white persons” and were therefore ineligible for citizenship) and discrimination for 4 years, Harry Truman signed the Luce-Celler Act into law in 1946.
Saund then became a naturalized citizen in 1949 and ran for judge in Imperial County California. During the campaign, someone asked him in the middle of a restaurant “Doc, tell us, if you’re elected, will you furnish the turbans or will we have to buy them ourselves in order to come into your court?” “My friend,” Saund responded, “you know me as a tolerant man. I don’t care what a man has on the top of his head. All I’m interested in is what he’s got inside.”On Election Day 1950, Saund won by 13 votes. In 1957, he then became the first Asian-American, first Indian-American, and first Sikh (or any non-Abrahamaic faith) to serve in Congress. Often just called “The Judge,” Saund staunchly supported the 1957 Civil Rights bill and other civil rights legislation, continuing his legacy of advocating for equal rights.
At Public Good, we provide tools that let people take action on the news. Whether it’s the refugee crisis, climate change, or a gang shooting, our goal is to allow people to help make the world better when they are motivated by good journalism. It’s not a completely new idea, but we revolutionized it by bringing machine learning to the party. In today’s overtaxed newsrooms, it’s not possible for reporters or editors to take on another responsibility. So for taking action to flourish, it needs to be automated and as simple to implement as a social media button.
For us, this begins with the problem of classifying news content. Until you know what a story is about, you can’t recommend actions. Unfortunately, the idea of a semantic web has failed us and there are no consistent tags or metadata to point in the right direction, and even if there were it’s likely the taxonomy used for navigating a news site (e.g. sports, entertainment, lifestyle, news) would differ from the taxonomy needed for taking action (e.g. violence, poverty, natural disasters) with no obvious mapping between them. So the most obvious first approach is to use machine learning classification algorithms. While we still use these methods as part of our overall system, we discovered they underperformed our expectations (how we expected them to perform on arbitrary textual data given our large training set and relatively small number of classes) and we’re beginning to understand why.
Most major classification algorithms make use of word frequency (or phrase frequency) as part of their analyses. When we first looked at the total number of unique words and phrases (high) this made us optimistic that these algorithms would perform well on our content. But a closer look reveals that the distribution of terms is highly imbalanced. A relatively small vocabulary of common words makes up the vast bulk of content (which we might have expected given that news content tends to be written for a wide audience with varying language skills and reading levels), while the big variety of words is substantially made up for proper nouns and other types of entities.
In retrospect, this isn’t surprising. News tends to be about people, places, and organizations. And unlike other kinds of textual data, these entities tend to enter the news vocabulary suddenly (e.g. “Hurricane Irma”) and often leave it just days or weeks later as the news cycle moves on. To a human brain, we often need only say a phrase like “Harvey Weinstein” to immediately register “sexual harassment”, but classifiers looking at months or years of historical data are proving less effective at making that determination — while the term is highly relevant, it’s only in a very small sample and, just weeks before it came to mean sexual harassment, it would have been a ringer for TV and movies.
While working to optimize our core classifiers, we’ve seen that some mitigation strategies can help a lot. First, online learning gets breaking news terms into the algorithms more quickly than batch training. Second, retiring old content from a training corpus as quickly as possible reduces the chance that a term that has become meaningful in breaking news will be associated with a previous meaning. And third, tweaking tolerances for stop terms makes a lot of difference for the bulk of language.
Most importantly, we learned that classifying the news accurately is a lot more complicated than setting up an off-the-shelf classifier and feeding it a bunch of data. Operational optimizations can help, but to be accurate on breaking news, ensemble ML methods and a breaking news team are critical.