Why context: It is not necessary that audiences will know the context of current news events.
Why automate: Newsrooms are optimized to stay on top of the news cycle and publish news fast and in vast quantities. Given this:
The need for structure: News covers a variety of topics — Sports, Politics, Business, Economy, Personal Finance — and there is no clear demarcation of where a particular topic will be found. We built upon the SIXTY user needs questions identified in modularjournalism.com by Clwstwr, Deutsche Welle, Il Sole 24 Ore and Maharat Foundation as part of the JournalismAI Collab Challenges 2021 / EMEA.
Over the last few months, the concept evolved as we discovered more nuances. Below are blog posts from then. The last piece that was published in the Polis LSE blog is the clearest version of what we intend to build. The other two demonstrate our thoughts in its evolutionary process.
The concept of context as product is not novel. It has been around in multiple shapes and forms. Below are some of the examples we curated for inspiration.
Examples from news products
Inserts in Semafor articles
Circa’s Follow Button
Examples from BigTech
Twitter’s Event Page
Twitter’s Community Notes
Amazon Prime Video X-Ray
Google News Full Coverage
The team discussed multiple design options but eventually concluded to stick to cards as a design concept.
The final UX: When a user is reading an article, they gets a prompt or nudge at the bottom sticky footer. For the copy of the prompt, we decided to use the user needs questions defined as part of modularjournalism.com. On clicking it, a bottom sheet opens and showcases context.
We referred to the algebra of modular journalism and from 60 user need questions, we came up with five card ideas for providing context.
Editors publish stories in relevant sections and subsections such as sports, cricket, tennis, world, US, politics, general elections, etc. However, online users are more interested in specific obsessions or hash tags, for example, Russia Ukraine War. Hence, the first step, was to invest in an algorithm to cluster the archive around news cycles instead of sections.
For this, we explored Topic Modeling algorithms. You can find our detailed evaluation in the below two blogposts:
To find the context we will use machine learning to go through all articles in a given newscycle which will pick the relevant information/facts that are then displayed in our five Context Cards. For this step, we explore two options:
Once we’ve bucketed the archive into topics, we intend to build the following cards/modules using ML:
[Timeline] What has got us here?
There are three ways to implement the timeline:
Method 1: The simplest option is to list out all related stories from the topic modeling model in descending order. To reduce the number of stories, we intend to combine each story with page views data and only show the stories that received higher page views than a certain threshold. However, this approach does not make for an elegant reading experience.
Method 2: We also considered using small language models like winkjs.org that identifies sentences with references to time. You can then pull these sentences out and then sort them to publish a timeline. However, this requires some behavioral shift in how Editorial writes articles and would also require significant post-processing.
Method 3: Ideally, we ought to have run another topic modeling algorithm on the stories from within a news cycle and cluster those stories into events. Finally, we run the summarization algorithm on top of stories within an event to generate the timeline.
[Expert Speak] What do key people say? How many points of view are there on this topic?
The list of opinion stories can be easily fetched from querying the content warehouse.
For extracting quotes, we intend to build on the quote extraction model built by The Guardian in an earlier iteration of JournalismAI.
[Data] What is the data?
To build this, we will reuse the broad methodology followed by the Guardian to extract quotes but deployed on extracting statements where data is quoted.
The tab mimics the “People Also Ask” feature from Google.
Our first thought was to use OpenAI’s GPT3 Q&A APIs. In fact, most GPT3 powered text editors or writing assistants provide a FAQs for SEO feature. However, OpenAI accepts text only in chunks of 500-1000 words. This means, the AI won’t generate Q&A after reading all the stories. This might not be correct.
Hence, we plan to build our own Question Answering models.
[Mentions] Who is it about? Who is involved?
For this, we intend to use Named Entity Recognition models. We tried out Spacy and observed significant noise which we reduced by filtering out entities recognized by NER but not found in Wikidata.
TOI’s internal CMS already does entity tags and maintains topic pages for these entities. Another approach could be to build on this itself instead of reinventing the wheel.
OpenAI released GPT-3’s latest upgrade—davinci-003 in November 2022. We decided to try it out for generating content for Context Cards. Here is a summary of what we found:
GPT-3 will surely help speed up the process to get the first draft. However, we’ll still need senior editorial supervision and review of the content generated before it can be published as context cards. Read more about findings in the blog below.
For this, we’ll be using Newscards, which is a modular content CMS. More on this in the below blogposts.