<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Local News Lab @ Brown Institute on Medium]]></title>
        <description><![CDATA[Stories by Local News Lab @ Brown Institute on Medium]]></description>
        <link>https://medium.com/@localatbrown?source=rss-402922c0fdd9------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*XrNa7Qg-0XBbxcW2MGEJWQ.png</url>
            <title>Stories by Local News Lab @ Brown Institute on Medium</title>
            <link>https://medium.com/@localatbrown?source=rss-402922c0fdd9------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 16:39:30 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@localatbrown/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Article recommendations and reader engagement: A case study in data science-driven local news…]]></title>
            <link>https://medium.com/localatbrown/article-recommendations-and-reader-engagement-a-case-study-in-data-science-driven-local-news-cdc564980360?source=rss-402922c0fdd9------2</link>
            <guid isPermaLink="false">https://medium.com/p/cdc564980360</guid>
            <category><![CDATA[recommendations]]></category>
            <category><![CDATA[journalism]]></category>
            <category><![CDATA[product-development]]></category>
            <category><![CDATA[local-news]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Local News Lab @ Brown Institute]]></dc:creator>
            <pubDate>Fri, 06 May 2022 17:43:42 GMT</pubDate>
            <atom:updated>2023-03-15T16:52:26.387Z</atom:updated>
            <content:encoded><![CDATA[<h3>Article recommendations and reader engagement: A case study in data science-driven local news collaboration</h3><h4>How The Local News Lab worked with The Philadelphia Inquirer and The Texas Tribune in our first Knight Foundation-funded cohort project</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*tRimmu-Sb5WfH_C4qTdGQA.jpeg" /><figcaption>Photo by <a href="https://unsplash.com/@zuizuii?utm_source=unsplash&amp;utm_medium=referral&amp;utm_content=creditCopyText">Lucas Hoang</a> on <a href="https://unsplash.com/photos/VgU5zIEy57A?utm_source=unsplash&amp;utm_medium=referral&amp;utm_content=creditCopyText">Unsplash</a></figcaption></figure><p>The Local News Lab at the Brown Institute is exploring different ways that AI can help boost reader revenue. Some AI tools provide assistance with time consuming tasks like selecting the stories to go behind a paywall and others are completely automated, like our recommendation engine that suggests a list of articles a reader might be interested in.</p><p>To be effective, our experiments require an understanding of a news outlet’s editorial values, their business needs and reader interests. We rely on collaborations with actual newsroom partners.</p><p>In October of last year, <a href="https://localatbrown.medium.com/a-new-collaboration-with-new-partners-ef5d07191c23">we started working with two local outlets — The Philadelphia Inquirer and The Texas Tribune</a>. We supported our partners from basic data collection to the deployment and testing of an automated recommendation system that compiles a list of ‘what to read next’ given the article you are currently perusing. Our work with these newsrooms involved scaling our system to handle their traffic — our goal was to support up to 10M monthly unique visits — . In the process, we led them through various workshops, each an opportunity for creative exploration around data and automation. While our goal was page-specific recommendations for readers, our development methods relied on tools that the news outlets could use long after our project finished — from “product thinking” to workshops that surfaced newsroom values around recommendation, automation and AI.</p><p>From development, to deployment and testing, these newsrooms were part of the whole process. They were tremendous partners to the lab in terms of our learning and technical improvements. As a practical matter, the recommendations were also a success! They boosted reader engagement (as measured by clickthrough rate, or CTR) by 10% on the Tribune and 16% on The Inquirer.</p><p>This project was about more than one product, though. With our cohort design, we sought to bring two different news organizations together and to help fill some gaps in expertise. To that end, we are proud of the work we’ve done. Here is a note we received from an engineer and partner at The Texas Tribune, whose permission we have to share:</p><blockquote>“We want to thank you again for all the work you and your colleagues have put into this project and all the assistance you provided through the A/B tests. We’re very excited that Trib editors and reporters will no longer have to spend so much time manually picking story recommendations. Should be a huge productivity gain for our entire editorial operation”</blockquote><blockquote><em>- Dan Simmons-Ritchie (Frontend Engineer, The Texas Tribune)</em></blockquote><p>Prior to this cohort-based project, we created and deployed an initial version of our recommendation system with our first experiment partner. Washington City Paper, a 40-year old publication covering Washington, D.C. that previously used a recommendation module featuring the most recently published articles and wanted to improve recirculation. Our system was trained using a machine learning approach known as <a href="https://www.educative.io/edpresso/what-is-collaborative-filtering">collaborative filtering </a>and based on an engagement metric of time spent on page (or “dwell time”). We ran our recommendations for five weeks on the Washington City Paper site, and with a sample size of roughly 500,000 sessions, we evaluated our recommendation module based on CTR. We found a 50% increase in CTR compared to our partner’s previous recency-based feed. The substantial gains demonstrate a desire readers have to more deeply engage with the paper’s content, but had previously lacked the ability to do so. The Washington City Paper needed new tools, tools that are typically only available for large publishers. Readers are hungry to engage with more local news content, and industry-standard data interventions like our recommendation module can deliver real value to local newsrooms and readers alike.</p><p>This site has significantly less traffic than our cohort partners’ but this first collaboration helped inform the type of machine learning models we chose, our framework for considering editorial values in recommendations, and to test our product in a production environment. We were excited to scale it to a whole new level with The Philadelphia Inquirer and The Texas Tribune.</p><p>One of the overarching goals of the lab is to communicate how we do our work, our successes, what we learn and how we can improve. What follows is a recap of our work with our first cohort in three main parts: <strong>the product process</strong>; <strong>scaling our system</strong>; and <strong>collaboration and communication</strong>.</p><h3><strong>Making a Recommendation “News Product”</strong></h3><p><strong>What we did well<br>Scaled the technology</strong>. Having our recommendation system already in production gave us a head start with this project. This meant that the lion’s share of the work over the six months would be scaling our infrastructure (as mentioned above). It also meant that we could explore recommendations conceptually with our partners.</p><p><strong>Workshopped the concept of “recommendations”</strong>. We held multiple workshops; we considered blue sky ideas inspired by platforms we’ve encountered in our daily lives as well as features that could be possible given the constraints in our current system. Our team’s data scientist and machine learning expert, Sam Petulla, also created and led a session focused on equity in recommendations, and prompted our partners to examine how their respective organizations’ values could inform all of their products, including recommendations</p><p><strong>Kept a solid roadmap</strong>. A solid roadmap kept us on track as experimental product innovation can be ambiguous work. We are especially proud of creating software development processes that built expertise and capacity within our cohort. Our “pair programming” sessions on data collection and API integration, for example, not only helped with our implementation, but also were novel and successful learning experiences for our partners.</p><p><strong>What we learned<br></strong>On the flip side, having a product already in production meant that we were not starting fresh, and that our partners had less control over the features our recommendation system were built upon; it was trained on a <a href="https://www.educative.io/edpresso/what-is-collaborative-filtering">collaborative filtering</a> model that, if we’d had more time, we might have compared it to a different type, perhaps a <a href="https://en.wikipedia.org/wiki/Semantic_similarity">semantic — or content — similarity</a> model). For our next cohort, we will attempt to tease apart our existing work, brief our partners on the component parts, and together decide on what new direction we will take. Our hope is this will provide a more creative and collaborative product planning process, be more engaging for our partners, and take us in a new and exciting direction.</p><h3><strong>Scaling a System</strong></h3><p><strong>What we did well</strong><br>Our technical team members, Sam Petulla, Ting Zhang, and Sylvan Zheng, did an extraordinary job in scaling our infrastructure from where it was (by all measures stable and successful running our system for a small local publication with modest traffic) to the point where it is now: supporting two distinct recommendation systems deployed on each of our cohort partners’ sites via APIs, both of which have significantly more traffic. To achieve this, Sylvan scaled our codebase so that we can more easily onboard additional newsrooms into our data collection and processing systems. This work has resulted in a 98% time savings in fetching data. Also our model can now accommodate 4x as much data as our initial prototype, with a training speedup of 30–50x faster, and our API can handle 50 more requests per second, which represents a 10x speed improvement. In short: we accomplished a huge amount of scaling work in a short period of time.</p><p><strong>What we learned</strong> <br>Completing the amount of technical work that we did in this timeframe means we also accumulated a not-insignificant amount of “technical debt.” With more time, we would be able to ensure our <a href="https://www.guru99.com/test-coverage-in-software-testing.html#:~:text=Test%20coverage%20is%20defined%20as,conditional%20statements%20have%20been%20taken.">test coverage</a> was high, and put an automated deployment system in place rather than relying on manual processes as we currently do. For these reasons (and more), we have extended our second cohort project to 8 months to make room for such improvements.</p><h3><strong>Collaboration</strong> <strong>+ Communication</strong></h3><p><strong>What we did well</strong> <br>As a distributed and fully remote team with remote partners in different parts of the country, it was a challenge to create a collaborative and creative environment. We established a roadmap along a timeline so the team was aligned and working toward the same goals. We set up regular meetings and Slack channels for both real-time and asynchronous communication. At the lab, we fiercely respect our and our partners’ time. We worked hard to ensure everyone was prepared for our meetings by circulating agendas and notes in advance and our efforts paid off — synchronous sessions were punctual and efficient. Most importantly, we <em>listened</em> to our partners: when the team at The Texas Tribune told us they wanted to know more about A/B testing, we created a presentation on best practices and worked directly with them to ensure our tests were set up well and that they could institutionalize this learning.</p><p><strong>What we learned</strong> <br>Given the nature of the project and that we were starting off with a product to scale, rather than a blue sky, we had some built-in constraints (which are not always a bad thing). While this meant the core product was less a group collaboration, we did make a point of running workshops around recommendation features and priorities, and customized the system to each newsroom’s specific needs. For our next cohort, we will have a keen eye towards intra-cohort collaboration and facilitate even more cross-partner sharing of learning and expertise. One big change we’re making is that our second cohort will consist of three partners instead of just two.</p><p>Our next post will announce the start of our second cohort that we are currently selecting. New people, new partners, and new product all lie ahead — stay tuned to read about the next chapter of the lab.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=cdc564980360" width="1" height="1" alt=""><hr><p><a href="https://medium.com/localatbrown/article-recommendations-and-reader-engagement-a-case-study-in-data-science-driven-local-news-cdc564980360">Article recommendations and reader engagement: A case study in data science-driven local news…</a> was originally published in <a href="https://medium.com/localatbrown">LocalAtBrown</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[A new collaboration with new partners]]></title>
            <link>https://medium.com/localatbrown/a-new-collaboration-with-new-partners-ef5d07191c23?source=rss-402922c0fdd9------2</link>
            <guid isPermaLink="false">https://medium.com/p/ef5d07191c23</guid>
            <category><![CDATA[journalism]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[recommendation-system]]></category>
            <category><![CDATA[local-news]]></category>
            <dc:creator><![CDATA[Local News Lab @ Brown Institute]]></dc:creator>
            <pubDate>Tue, 26 Oct 2021 19:25:30 GMT</pubDate>
            <atom:updated>2023-03-14T19:26:24.026Z</atom:updated>
            <content:encoded><![CDATA[<h4>We are working with a pair of very exciting newsrooms on scaling our recommendation system for deeper reader engagement</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*E_iPYLE9DnY8K-UVHQoSYw.jpeg" /></figure><p>We have been busy at work throughout the summer, running and evaluating <a href="https://medium.com/localatbrown/recommendations-part-1-the-need-for-enhanced-audience-behavior-insight-995dd6837e0">our experiment</a> and hiring some new team members. Now, with support from <a href="https://medium.com/localatbrown/local-news-lab-awarded-knight-foundation-grant-for-ai-initiatives-43234d68a9b5">a grant from the John S. and James L. Knight Foundation</a>, we are kicking off a new project that we’re very excited about: we are thrilled to announce the start of our inaugural newsroom cohort, partners with whom we will be collaborating on the scaling of <a href="https://medium.com/localatbrown/recommendations-part-2-an-experiment-to-test-personalized-calls-to-action-c5fc93688419">our data-informed recommendation system</a>. This small but mighty cohort consists of <a href="https://www.inquirer.com/">The Philadelphia Inquirer</a> and <a href="https://www.texastribune.org/">The Texas Tribune</a>.</p><p>We will be working closely with the product teams at both of these illustrious news organizations in order to:</p><ul><li>iterate on and customize our successful recommendation system and deploy it on our partners’ sites;</li><li>help explore their data analytics and provide insights that could help improve their reader engagement strategy; and</li><li>share learning and expertise and identify how we can continue to create community around the intersection of editorial, revenue and technology.</li></ul><p>Ultimately, our goal with this project is increasing revenue-generating reader engagement and supporting local newsrooms’ financial sustainability.</p><p>We went through a very intentional process to acquire these partners, promoting a call for applications through social media and our network of local newsrooms. Among our top considerations were the communities served, geographic location, and technical capabilities. After receiving about two dozen applications, all from very worthy organizations doing important work, we shortlisted four and are ecstatic to have selected the Inquirer and the Tribune. The geographic diversity of these two newsrooms along with the range of communities they serve fit well with the values of our team. Their websites are published using custom platforms which will necessitate us collaborating closely with their in-house engineers.</p><p>Our first task is collecting our partners’ data so we can start adapting and training our machine learning models to fit their needs. We will soon begin to meet with them regularly to discuss ways we can improve our current recommendation systems and align it with their business goals.</p><p>As we get deeper into the project, we will share more; it is part of our mission to help the wider local news community and elevate knowledge and expertise. We will be collaborating with <a href="https://knightfoundation.org/articles/ai-for-local-news-advancing-business-sustainability-in-newsrooms/">our fellow grantees within the Knight initiative: The AP, NYC Media Lab and Partnership on AI</a>, which is a new and exciting way of working for us. We will also be engaging with a second cohort project in Spring of 2022, so stay tuned (here on Medium or <a href="https://twitter.com/LocalAtBrown">follow us on Twitter</a>) for more information on that in the months ahead. For now though, welcome to our partners, The Philadelphia Inquirer and The Texas Tribune — we are delighted to have you aboard!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=ef5d07191c23" width="1" height="1" alt=""><hr><p><a href="https://medium.com/localatbrown/a-new-collaboration-with-new-partners-ef5d07191c23">A new collaboration with new partners</a> was originally published in <a href="https://medium.com/localatbrown">LocalAtBrown</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Local News Lab awarded Knight Foundation grant for AI initiatives]]></title>
            <link>https://medium.com/localatbrown/local-news-lab-awarded-knight-foundation-grant-for-ai-initiatives-43234d68a9b5?source=rss-402922c0fdd9------2</link>
            <guid isPermaLink="false">https://medium.com/p/43234d68a9b5</guid>
            <category><![CDATA[columbia-university]]></category>
            <category><![CDATA[local-news]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[product]]></category>
            <category><![CDATA[journalism]]></category>
            <dc:creator><![CDATA[Local News Lab @ Brown Institute]]></dc:creator>
            <pubDate>Thu, 13 May 2021 13:12:38 GMT</pubDate>
            <atom:updated>2023-03-15T16:54:12.426Z</atom:updated>
            <content:encoded><![CDATA[<h4>The Brown Institute’s Local News Lab joins three other recipients in a collaborative effort to use AI to help local newsrooms</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/792/1*XOhuud01QI0td4M77sWbxg.jpeg" /></figure><p>The Local News Lab at the Brown Institute for Media Innovation is thrilled to announce that we have been awarded a $500,000 grant over two years from the <a href="https://knightfoundation.org/articles/ai-for-local-news-advancing-business-sustainability-in-newsrooms/">John S. and James L. Knight Foundation as part of a $3 million initiative supporting applications of artificial intelligence to support the sustainability of local news organizations</a>. We are grateful to Knight for supporting our efforts and we are so excited to collaborate with the other recipients of this initiative: The Associated Press, with which Brown has previously worked on prototyping a tool to help automate some of the repetitive tasks involved in covering Long Island school board elections — from voter guides to “night of” results; the NYC Media Lab will be a huge complement to our work and will bring their convening power as we seek to help create community around the work; and new to our sphere, Partnership on AI will be providing research into the ethical considerations of AI and how it can be used across the entire news ecosystem. If you work at a local or community-based newsroom and this sounds interesting to you, please <a href="https://localnewslab.typeform.com/to/hmK2oOEM"><strong>fill in this form</strong></a> to let us know.</p><p>Our role in this collaborative effort has three main pillars: to <strong>devise and deploy</strong> <strong>experiments</strong> to test new data- and AI-informed approaches that enhance reader revenue; to <strong>accelerate development and distribution</strong> of open-source software projects that automate time-intensive decisions and often manual implementation of subscription strategies; and to <strong>build community </strong>by assembling working groups, documenting the team’s learnings, and establishing a platform where news organizations can share and build on each other’s experiences testing business strategies.</p><p>National newsrooms, with their sizable audiences and engineering resources, are applying AI to increase reader revenue. For example, The New York Times produces personalized newsletters, the Washington Post detects evergreen articles that can be reshared, and BuzzFeed automates their social publishing process — all contributing towards higher engagement, subscriptions, or donations. In contrast, local newsrooms often lack the data readiness and staff to implement and iterate on such strategies. This initiative will allow us to create a sustainable environment for ongoing testing — incubating a culture of experimentation among local newsrooms, providing user-friendly open-source tools, and “scaling up” local knowledge in ways that previously only large newsrooms could achieve.</p><p>We can’t wait to begin collaborating with our partners and would love to hear from anyone who works at a local or community-based newsroom and is looking to optimize their reader revenue strategies and learn more about the intersection of AI, editorial and revenue. We want to help, so if you’re interested in working with us, please <a href="https://localnewslab.typeform.com/to/hmK2oOEM"><strong>fill in this form</strong></a> and let us know who you are and why you’re interested in the project.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=43234d68a9b5" width="1" height="1" alt=""><hr><p><a href="https://medium.com/localatbrown/local-news-lab-awarded-knight-foundation-grant-for-ai-initiatives-43234d68a9b5">Local News Lab awarded Knight Foundation grant for AI initiatives</a> was originally published in <a href="https://medium.com/localatbrown">LocalAtBrown</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How machine learning can help sustain local news]]></title>
            <link>https://medium.com/localatbrown/how-machine-learning-can-help-sustain-local-news-7d1414b950f1?source=rss-402922c0fdd9------2</link>
            <guid isPermaLink="false">https://medium.com/p/7d1414b950f1</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[local-news]]></category>
            <category><![CDATA[journalism]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[publishing]]></category>
            <dc:creator><![CDATA[Local News Lab @ Brown Institute]]></dc:creator>
            <pubDate>Tue, 24 Nov 2020 16:37:30 GMT</pubDate>
            <atom:updated>2023-08-02T18:09:40.134Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="Person with big shoes and with one hand on hip and the other pointing to a graph with an arrow going up." src="https://cdn-images-1.medium.com/max/800/1*TpIDnWyqgCto4yirqX66nw.png" /><figcaption>Illustration by <a href="https://blush.design/artists/elina-cecilia-giglio">Elina Cecilia Giglio</a></figcaption></figure><p>At Brown’s Local News Lab we are using Machine Learning to “optimize the ask”</p><p>Hello from <a href="https://lnl.brown.columbia.edu/">the Local News Lab at The Brown Institute</a>! Since our last post, we have been busy connecting with a wide variety of newsrooms from the west side of Manhattan to Harare, Zimbabwe. Our machine learning engineers have been working on modelling and as a team we are planning some discrete experiments that will help us establish the direction of <a href="https://medium.com/localatbrown/introducing-the-brown-institutes-local-news-lab-fc38638c8b18">our first product</a>.</p><p>Machine Learning (ML) and Artificial Intelligence (AI) are both very buzzy terms that have been floating around tech spaces for decades and journalism more recently, but this post is for anyone who is fairly new to the concept of ML and would like to know more about how it might help local newsrooms and their financial sustainability. Mark Hansen, the Director of the Brown Institute says:</p><blockquote>“Journalism is becoming a computational exercise. Of course, computation is an important tool in reporting, and we make a host of data-informed decisions about our content right down to its placement on the website. But through computation we have also experimented with story automation and have created a host of fresh ‘news products.’ We have even used advanced ML to assess the diversity of the subjects we report on and the sources we turn to. But these all rally computation to create experiences for our readers. Now at Brown, we are exploring how computation opens up creative new opportunities to invite readers to become subscribers, members or donors.”</blockquote><figure><img alt="Person with long hair posing a question and speaking with ellipses in a speech bubble." src="https://cdn-images-1.medium.com/max/800/0*445eVGExKO4kH7w-" /></figure><p><strong>Umm…what is Machine Learning again?</strong></p><p>If you are still a bit fuzzy on what ML is, here are two short videos that do a very good job at explaining it: <a href="https://www.youtube.com/watch?v=f_uwKZIAeM0">this one</a> and <a href="https://www.youtube.com/watch?v=F1wlCerC40E&amp;feature=emb_logo">this other one</a>.</p><p>ML is how Google and Facebook choose which ads to surface on the websites you browse. It’s how your favorite video streaming app makes recommendations on what to suggest you watch next. Michael Jordan, a leading ML researcher, <a href="https://medium.com/@mijordan3/artificial-intelligence-the-revolution-hasnt-happened-yet-5e1d5812e1e7">defines the field </a>as blending “ideas from statistics, computer science and many other disciplines… to design algorithms that process data, make predictions and help make decisions.” He sees ML as the basis for a new discipline of “Intelligent Infrastructure, whereby a web of computation, data and physical entities exists that makes human environments more supportive, interesting and safe.”</p><p>What does that mean for journalism? Certainly the people and processes behind the news make decisions that are more informed by data and computation, but it’s time to think about ML’s impact on the industry holistically — from content creation, to distribution and engagement, to business sustainability.</p><figure><img alt="Person pointing to graphs and a technology stack." src="https://cdn-images-1.medium.com/max/800/0*ejxAy0AN0HzF7d8o" /></figure><p><strong>Machine Learning is already all around us</strong></p><p>Reader activity across news sites has been tracked and analyzed using some form of ML for years. The industry has adopted engagement metrics that summarize reader behaviors and provide benchmarks against which publishing strategies are ultimately evaluated. Recently, the platforms that publishers use to deliver news and other content have greatly diversified, and so too has the variety of ways we can now quantify a reader’s overall experience with a publisher.</p><p>With falling revenues from advertising, the reader (whether they be a donor, supporter, member or subscriber) has become a more critical and direct contributor to news sites’ revenue streams. ML is being applied to optimize business decisions in countless other industries — examples of Jordan’s Intelligent Infrastructures. At Brown, we are exploring how to make dynamic, personalized, and impactful choices about the forms in which we offer content to news readers, and the ways in which we ask for their support — or in much trendier (and pithy) words, to “optimize the ask”.</p><p>With the ability to adapt a publisher’s behaviors in real time, and uniquely for each reader, there are a myriad of possibilities for designing new experiences around content. Newsrooms, for example, have experimented with various kinds of recommendation strategies and personalized feeds of stories and newsletters. Each of these are attempts to infer a reader’s interests by looking at their history with a site, or to predict content they would find useful given the activities of others who have engaged in similar behaviors. The latest ML tools are being used to optimize these individual recommendations, reader-by-reader. For instance, The Dallas Morning News has experimented with a separate paywall for their popular election voter guide that gave readers the option of choosing their own price to subscribe starting from $0.00.</p><figure><img alt="Person with hair wrap typing on laptop while images of technology surround them." src="https://cdn-images-1.medium.com/max/751/0*q5Yy2PYJ8PDfoRR3" /></figure><p><strong>Optimizing the ask</strong></p><p><a href="https://spiegel.medill.northwestern.edu/_pdf/what-causes-subscribers-pay-for-local-news.pdf">There is research that supports what many in the news business already can tell you they know from gut instinct and their own existing metrics:</a> that readers who return to their site on a regular basis, and readers who engage at higher rates with content relevant to their location are more likely to subscribe.<a href="https://reutersinstitute.politics.ox.ac.uk/sites/default/files/2019-05/How_media_companies_use_data.pdf"> Many newsrooms around the world are already using data to influence their publishing, subscription and engagement strategies.</a> By incorporating ML, we encourage cross-organizational discussions about readers, their interests and habits, and the data we have to represent our ideas. ML can help us think creatively about the ways we might structure our content to provide opportunities for an audience to support our business, while enabling experiments to see what works.</p><p>At Brown’s Local News Lab, we like to say our product will help get the right message in front of the right person at the right time — optimizing the ask. Because if we can learn what that sweet spot is — when and why a casual reader is most likely to hit the “subscribe” (or “join” or “donate”) button — newsrooms should see a boost in reader revenue, helping them on their path to financial sustainability, or whichever sort of engagement they wish to create. While “paywall” is indeed the easiest way to describe our product, it is actually more of a tool to facilitate conversion. Ultimately we envision a newsroom creating not just a reporting plan for a particular story, together with a publication and social media schedule for distribution, but also a conversion strategy — something that is structured and aligned with the content the newsroom is generating, and its publication.</p><p>While the initial allure of ML is that we can imagine new paywall functions and optimize their use, there is much more to the exercise. ML can help newsrooms better understand their business. What brings in subscriptions? Which content resonates? How should paywalls and other prompts like registration and newsletter subscriptions be deployed? Who is most likely to register or subscribe or even churn, and under which conditions and when? Unfortunately, not every newsroom has access to data scientists or machine learning engineers who can develop the technology to enable this level of insight.</p><p>This is where we come in.</p><p>In a nutshell, our goal is to help fill a pressing need in local news of high level data science that until now has been unattainable, and in doing so, deliver a product that uses sophisticated ML that will lead to increased revenue and a more financially sustainable product. We also have the experience to know the limits of ML — what’s plausible and what’s hype. Sorting fact from fiction is another service we can provide our local newsroom partners.</p><p>Please let us know if you have any questions about ML or our project. Feel free to drop me, <a href="/service/mailto:jw4082@columbia.edu">Hannah Wise, News Partnerships Lead</a>, a line.</p><p>And thank you for reading!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7d1414b950f1" width="1" height="1" alt=""><hr><p><a href="https://medium.com/localatbrown/how-machine-learning-can-help-sustain-local-news-7d1414b950f1">How machine learning can help sustain local news</a> was originally published in <a href="https://medium.com/localatbrown">LocalAtBrown</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Introducing The Brown Institute’s Local News Lab]]></title>
            <link>https://medium.com/localatbrown/introducing-the-brown-institutes-local-news-lab-fc38638c8b18?source=rss-402922c0fdd9------2</link>
            <guid isPermaLink="false">https://medium.com/p/fc38638c8b18</guid>
            <category><![CDATA[paywall]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[columbia-university]]></category>
            <category><![CDATA[journalism]]></category>
            <category><![CDATA[local-media]]></category>
            <dc:creator><![CDATA[Local News Lab @ Brown Institute]]></dc:creator>
            <pubDate>Mon, 14 Sep 2020 20:49:13 GMT</pubDate>
            <atom:updated>2020-09-14T20:49:13.698Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*b601IIUhRXj3YTvPJ0PJ-A.jpeg" /><figcaption>Photo via Pexels</figcaption></figure><p>The Brown Institute for Media Innovation at the Columbia Journalism School is exploring the application of machine learning (ML) and other technologies to support local newsrooms — both advancing their editorial missions as well as creating new business opportunities to engage readers. As is now the hallmark of Brown Institute projects, our approach is collaborative and interdisciplinary, developing responsible technology in the service of journalism’s public mission.</p><p><strong>Who?</strong> <a href="https://lnl.brown.columbia.edu/index.html">Meet the Local News Lab. We are a new team of engineers, designers, data scientists, and journalists</a> with over two decades combined of experience in media and digital news products. We have varied backgrounds in both legacy and digital-first start up journalism and academic education in engineering and data science.</p><p><strong>Why?</strong> In the last two decades, journalism, as a profession and as a business, has faced a difficult transition. The subjects of its reporting, the “powerful,” are now as likely to act through the accumulation of data and algorithms as they are through the exercise of traditional political, cultural or social mechanisms. In the same period, journalism’s core means of production and distribution have become digital, with social media and other platforms forcing a reexamination of readers’ relationships with traditional outlets and the ways they can support their businesses.</p><p>In short, journalism is becoming an exercise in computation — from the ways we report and tell stories, to how we understand and engage our readers. This shift has placed newsrooms under tremendous economic pressures, and only a handful have the capacity to keep up with the technological changes reshaping the field. It is difficult for all but the largest newsrooms to provide creative direction in the development of substantial new forms of journalism and engagement strategies to support monetizing this content. Small- to medium-sized outlets have very few choices when it comes to this kind of innovation, and often simply do without or are forced to acquire third party solutions at considerable expense and without in-house technical expertise.</p><p>Journalism needs broad leadership to envision a new future for the profession, one that mobilizes the power of technology directly in the service of news organizations. Achieving this leadership requires both a commitment to journalism’s public mission, while meeting our new responsibility to sustain technical and creative innovation, placing special emphasis on local outlets.</p><p><strong>What?</strong> Our primary goal is to support the financial sustainability of local newsrooms. We are creating a culture of interdisciplinary experimentation within journalism, one that produces easily and widely shared strategies for approaching current editorial and business-side challenges. We are exploring traditional paywall tactics along with more innovative and broad ways that an organization can convert casual readers into loyal fans that support its journalism with their dollars and attention.</p><p>These strategies will be implemented through open source software and readily deployed systems — “news products.” Our approach to innovation will be collaborative, involving multiple newsrooms and our development team will work with partner news organizations from design through engineering and deployment. Our framework for product development is nimble enough that ideas can be quickly tested and developed to respond to the needs of our changing profession in a timely way.</p><p>These efforts are designed to produce a stream of new strategies and accompanying open source tools in an industry that desperately needs to make the most of its contemporary involvement with computation. We believe a university is the natural and ideal point of coordination for these efforts, with its mandate to assess the present and future needs of the industry, and to provide continuing education as the nature of the profession shifts.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*GtRDmGWjHMAELNkDKIBGyg.jpeg" /><figcaption><a href="https://www.pexels.com/@goumbik">@goumbik for Pexels</a></figcaption></figure><p><strong>How?</strong> As the first of a number of anticipated projects incubated by Brown, we are developing an open source “smart” paywall that deploys ML to go beyond one-size-fits-all approaches to audience engagement. It will help fill a resource gap, in which a handful of large news outlets have this development capacity, but the vast majority of daily newspapers — almost 1,300 — do not. The word “paywall” seems insufficient in this context; while the product will indeed be a gate to the content, the intention is for it to be flexible enough to offer newsrooms the ability to use it in a number of ways that may not have anything to do with money (if they so choose), helping build engagement, better understanding of audiences as well as having the capacity to drive subscriptions, memberships or solicit donations. In this way, the product is the place where business, newsroom and reader needs all meet — it can become a place of creativity and innovation.</p><p><strong>What’s next? </strong>The work is underway and we are actively looking for organizations to collaborate with. If this sounds like something your newsroom might be interested in, please get in touch with <a href="/service/mailto:jw4082@columbia.edu">Hannah Wise</a>, News Partnerships Lead about becoming a development partner.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fc38638c8b18" width="1" height="1" alt=""><hr><p><a href="https://medium.com/localatbrown/introducing-the-brown-institutes-local-news-lab-fc38638c8b18">Introducing The Brown Institute’s Local News Lab</a> was originally published in <a href="https://medium.com/localatbrown">LocalAtBrown</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>