Automated content production

Automated News Content Production Using Natural Language Generation

Created by : Rated :3.9 9895 views

Last Updated: 2023-03-21 08:03:21 English Course Type: Self Learning

How Automated Content Production (ACP) relates to information reporting, from the journalistic point of view.
How Automated Journalism works and companies who currently offer the best Natural Language Generation software that facilitates automated journalism
How Big Data is used in Automated Content Production and the part Natural Language Generation plays

Automated News Content Production Using Natural Language Generation, for Non-Technicals, Leaders, Managers, Freshers and Beginners.

Natural language generation (NLG) is a technology that transforms data into clear, human-sounding narratives—for any industry and application.

Top news publishers, content creators, health companies, finance institutions, sports companies, energy companies, oil companies, entertainment companies and many more industries are already using Natural Language Generation to increase the SPEED, SCALE and TIME of creation of content and reports.

Facts!!

Associated Press (AP) once upon a time only had the capacity to produce 300 financial reports a quarter, leaving thousands of potential company earnings reports unwritten.

Today, using Natural Language Generation (NLG), AP produces over 5,000 quarterly recaps, freeing up 20% of journalists’ time that was previously spent on writing recaps. This an almost 15-fold increase over its manual efforts.

Yahoo! Sports uses NLG technology to create over 70 million match recaps and reports and every single one of them is unique.

This increased time spent on page for website visitors, delighting and delivering a massive user base.

Are you looking to turn your data into clear natural language? Are you tired of writing manual reports? Or narrating huge amounts of data manually? Or wondering what the future of Artificial Intelligence (AI) holds for you a content creator, writer, manager, leader, researcher? Then this course is for you.

This course is a single installation of a broader advanced 3-part course called ‘Automated Content Production and News Algorithms’. It consists of 3 modules and 23 learning videos including the transcript and practice questions.

This Part of the course covers;

An Overview of Automated Content Production (ACP) and its techniques especially as it relates to information reporting, from the journalistic point of view.

How Big Data is used in Automated Content Production and the part Natural Language Generation plays.

How Automated Journalism works and companies who currently offer the best Natural Language Generation software that facilitates automated journalism.

Top news Publishers using Automated Content Production (ACP) to create news with minimal human input, and to generate personalized content while increasing engagement.

The value Automated Content Production (ACP) brings to journalism, the potential it delivers, and its limitations, which ensures that humans also play a huge role in the process.

A step-by-step guide on how to use Arria Studio Natural Language Generation Software to automatically narrate data or tell stories from a data sheet.

How algorithms help to facilitate news distribution and are hugely contributing to news consumption.

How news publishers can leverage the power of algorithms to get their readers to keep coming back. News publishers already doing this.

Categorization of algorithms based on the decisions they help us make

The roles algorithms play in determining what we see and do not see. How algorithms act as gatekeepers of information.

Content optimization and audience analytics

How news publishers are optimizing news creation using a wide range of tools that facilitate better content creation.

Content optimization, sentiment analysis and content dissemination, using election as a case study.

You will get 23 videos of learning content with transcript and practice questions

Besides the video materials, there are also transcripts of the videos, and practice questions to help guide and reinforce your learning.

Willingness to learn and practice the learning
A laptop or mobile phone with internet connection

Non-Technicals
Leaders
Managers

Section 1 : Introduction to automated content production 10 Lectures 00:19:46
Lecture 1 :
Introduction to automated content production Preview
Hello and welcome to module 4 of the Automated Content Production and Algorithms course. In this module we will talk about – Automated Content Production, Core. We will discuss; I. What Automated Content Production really means II. How Automated Journalism works III. Newsrooms already using automated journalism IV. News organizations and applications for automated news V. Value AI automation brings to journalism VI. Limitations of Automated Content Production Also as a reminder, after watching the videos, please proceed to read the three documents that are added to this module. Also, please ensure you take the quiz.
Lecture 2 :
Automated Content Production
Overview Upon looking at this screenshot of an article by Associated Press, one would think this a normal story written by a journalist until you see the footnote which clearly states that it was created by a software algorithm. The article looks almost perfect, providing all key information finance watchers and forecasters are interested in. The technology, technique and innovation in which this master piece was created is what we call Automated Journalism. This can also be termed Robotic Journalism. The Columbia Journalism Review Guide on Automated Journalism defines it as the process of using software or algorithms to automatically generate news stories without human intervention—after the initial programming of the algorithm, of course. In this technique, the human decides on what data is to be used, and grants the software algorithm access to that data which is in a structured form. The machine collects, analyzes, interprets and summarizes. In a case where the data is not structured, the human has to find, cleans and structure it in a format easy for the algorithm to interpret. There is also the human input which has to do with assignment of functions, branching sentences or phrases using synonyms to create variability, and creation of a writing style. Different writing styles can be created to suit different beats. Let’s call this the creation of a guiding template for the algorithm. Subsequently after, the algorithm performs the rest, creating content faster, tirelessly and at scale, with minimal errors. The only error accruable is error in the data which was already there in the input. (This part we will discuss more in the Algorithmic Investigation and Reporting Module) Now, there are constant fears on what this means for journalisms. Will journalists’ jobs be at stake? The answer is no. Automated journalism exists solely to augment the fantastic job already being done by journalist, enhancing their power and abilities to be more efficient while focusing on other areas in which they were lacking.
Lecture 3 :
How does Automated Journalism work?
Curriculum You no longer have 10 minutes of video content available for free preview which may impact enrollment rate for your course. Please enable free preview for another video lecture so that you meet this minimum requirement or we will enable one for you automatically. Learn More. If you’re intending to offer your course for free, the total length of video content must be less than 2 hours. Section 1: Introduction to Automated Content Production Lecture 1: Automated Content Production (Preview enabled) Lecture 2: Automated Content Production Lecture 3: How does Automated Journalism work? Automated_Content_Production_4.mp4 03:49 Edit Content Free Preview: Downloadable: How does Automated Journalism work? Automated Journalism uses the power of Big Data and what we all Natural Language Generation (NLP). Big Data: These are extremely large data sets that may be analyzed computationally to reveal patterns, trends, and associations, especially relating to human behavior and interactions. Natural Language Generation (NLP): This is a software process that transforms structured data into natural language. It can be used to produce long form content for organizations to automate custom reports, as well as produce custom content. Most of the solutions I have seen work like this: You import data, or extract data from a database. You build a template - a writing style, assign functions like branching sentences or phrases using synonyms to create variability. The algorithm takes your input and runs with it, analyzing, summarizing and narrating the data into almost human narratives (all which happens in less than 10 seconds as soon as you hit an ‘apply’ button. The companies I have seen so far with this technology at its best include; Arria NLG, Automated Insights and Narrative Science.
Lecture 4 :
Newsrooms already using automated journalism
tomated Content Production LIVE 1hr 37min of video content published Curriculum You no longer have 10 minutes of video content available for free preview which may impact enrollment rate for your course. Please enable free preview for another video lecture so that you meet this minimum requirement or we will enable one for you automatically. Learn More. If you’re intending to offer your course for free, the total length of video content must be less than 2 hours. Section 1: Introduction to Automated Content Production Lecture 1: Automated Content Production (Preview enabled) Lecture 2: Automated Content Production Lecture 3: How does Automated Journalism work? Lecture 4: Newsrooms already using automated journalism VIDEO_5_-_Automated_Content_Production.mp4 03:42 Edit Content Free Preview: Downloadable: Newsrooms already using automated journalism In recent years, top news organizations have been leveraging this technology to maximize content production. Yahoo! Sports uses this technique to produce over 70 million reports and match recaps—each one unique—that help engage, monetize, and delight its massive user base. It has helped increase time spent on page by readers, hence adding over 100 years of incremental audience engagement. The Associated Press (AP) used this technique to automate NCAA Division I men’s basketball previews during the 2018 season allowing their journalists to focus on writing critical, qualitative articles. AP at one time only had the capacity to produce 300 financial reports a quarter. Today, over 5,000 quarterly recaps have been produced, freeing up 20% of journalists’ time that was previously spent on writing recaps Other organizations like Bloomberg and Thomson Reuters also use NLG techniques to extract key figures from press releases and insert them into pre-written templates to automatically create news alerts for their clients. “You can’t compete if you don’t automate.” - Reginald Chua, executive editor for editorial operations, data, and innovation at Thomson Reuters.
Lecture 5 :
News organizations and applications for automated news
News organizations and applications for automated news Bloomberg’s Cyborg: An AI that identifies key data points in earnings reports for thousands of companies and publish headlines and articles in seconds. However, it also needs humans to tell it what to look for, where to look for it and to guarantee its independence and transparency to readers. Toutiao by ByteDance: Toutiao which means (Headlines) is a news aggregator that uses AI-powered personalisation engines to source and curate daily news and articles for its 120 million daily users via its 4000 partner sites. Radar by The Press Association: Rather fuses journalism skills and AI tools to create what they call ‘Live Tech’ – analysing data and developing a tailored algorithm to generate stories in hours, not days or weeks. In June 2018 they launched a daily news service for local newsrooms in the UK. Since then, their team of five reporters has filed 250,000 articles. The Times of London’s JAMES: The Acronym JAMES means ‘Journey Automated Messaging for higher Engagement through SelfLearning’, it uses data insights and predictive data models to get to know the habits, and preferences of readers, interests. It acts as a digital butler, to accelerate subscriptions growth and reduce churn
Lecture 6 :
The value AI automation brings to journalism
Lecture 7 :
Limitations of Automated Content Production
Lecture 8 :
Automated Content Production
Lecture 9 :
Automated Content Production
Lecture 10 :
Quiz
Quiz
Section 2 : Algorithms in News Distribution 6 Lectures 00:10:08
Lecture 1 :
Algorithms in News Distribution
Hello and welcome to module 5 of the Automated Content Production and Algorithms course called – Algorithms in news distribution. This module will cover; I. How algorithms help in news distribution II. How a change in algorithm can make or mar a news platform III. Understanding algorithms based on their types of decisions IV. Algorithms as a gatekeeper of information Also as a reminder, after watching the videos, please proceed to read the three documents that are added to this module. After this, please ensure you take the quiz.
Lecture 2 :
How algorithms help in news distribution
How algorithms help in news distribution On May 25, 2020, George Floyd, a 46-year-old black man, was killed in Minneapolis, Minnesota, during an arrest for allegedly using a counterfeit bill. Derek Chauvin, a white police officer, knelt on Floyd's neck for almost nine minutes while Floyd was handcuffed and lying face down in the street, begging for his life and repeatedly saying "I can't breathe". A second and third officer further restrained Floyd while a fourth prevented bystanders from intervening. During the final three minutes, Floyd was motionless and had no pulse while Chauvin ignored onlookers' pleas to remove his knee, which he did not do until medics told him to. By morning of the 26th Google searches for “George Floyd” were trending indicating a surge of interest as the public frantically searched for information and further details of what really transpired. Search engines and social media platforms played a key role in the dissemination of the news. But were those search engines providing accurate information? Were they providing diverse or balanced information? As the media rolled out headlines upon headlines and the news spread like wild fire, hoaxes, conspiracy theories and other falsehoods began spreading on Facebook and Twitter. Two very significant false hoods were posts suggesting that George Floyd was alive and that the Billionaire investor George Soros and donor to the Democratic party was funding the demonstrations against police brutality. Now upon a proper investigation for the most likely source of news when a Google search is done on George Floyd for every minute for 24 hours, one would find a huge lack of diversity in the news sources. In the 24-hour period, the investigation would show a handful of the same news sources being responsible for the “Top Stories” menu on Google search results. One would discover that the top 6 of those news sources accounted for 85% of the links to stories that showed. The platforms include New York Times, Aljazeera, BBC, NBC News, CNN, Sky News. Social media like twitter also played a key role as the ‘George Floyd went up the trends list. In news consumption, search engines and social media platforms play key roles as their algorithms determine the information the public see and engage with.
Lecture 3 :
Winning and Losing with Algorithms
Winning and losing with algorithms A change in Algorithm can shoot up the traffic on a news platform or it can reduce it drastically. The publishing platform Medium was launched in 2012 by Twitter co-founder Evan Williams. The platform uses an intelligent algorithm primarily based on the length of time users spend reading articles to recommend content to reader. The out turn of this is that users are going to find content that spans the reading time they are used to. This simple feature will keep the user coming back. Google, Facebook and Twitter are highly responsible for referral traffic to websites. In 2017 Facebook decided to prioritize posts from friends and family in its newsfeed algorithm. This reduced referral traffic from Facebook by 15 percent, i.e., from 40 percent to 25 percent. This in turn dropped the traffic of several news platforms by several pegs. Algorithms make it easier for people to find content and vice versa. The recommended stories you see at the end of every story on any news site are calculated via algorithm. These algorithms take into consideration the news content you click. The Times’s algorithm can display more than 160 different layout combinations, changing to accommodate different types of articles and images, and for emphasis. Small differences in labeling and typography allow the algorithm to use design to signal editorial importance.
Lecture 4 :
Algorithms and Categories
Algorithms and categories As mentioned in a previous module, Algorithms can be categorized based on the types of decisions they make. Prioritization, for example, ranks content, prioritizing one content over the other. Association marks relationships between entities, such as articles or videos that share subject matter of features. Filtering involves the inclusion or exclusion of certain information based on a set of criteria. Classification ranks content based on the similarities of subject matter Calculation, this can be viewed in terms of a ranking algorithm selecting articles by stat, for example by number of Up votes it has.
Lecture 5 :
Algorithms as Gate Keepers
Algorithms as gate keepers Algorithms play a key role in determining what is visible and what is not. When algorithms serve users contents based on certain decisions they make based on their consumption habits, that means that every other information that could have been useful to the user is excluded from their sights. Algorithms are responsible for shaping viewpoints on several societal issues even if these viewpoints are not true. During the first waves of the George Floyd protests, there were coordinated attempts at misinforming the public circulating online; there were posts that read “George Floyd is alive, this an intentional scheme to start a race war”. Another read; “Get paid to be a Professional Anarchist!”. And algorithms would do what they do best, spread these information, hence helping to shape thoughts. Since many people searching for information online are not aware of the extent algorithms help drive agendas, they are unable to make the decision to look outside the information pocket provide by the algorithms. Finally, due to these reasons, several traditional media platforms and non-governmental organizations who value truth and best practices take it upon themselves to constantly fact-check information, especially the viral ones. Today, many news platforms are aware of how algorithms influence their content and their readers, and as such they are developing their own curation algorithms, and proclaiming their freedom hence, shrinking their dependency on algorithms created by non-journalistic institutions. In the next video I’ll get into Content Optimization and ways understand how your content performs. That’s it for now.
Lecture 6 :
Quiz
Quiz
Section 3 : Content Optimisation 10 Lectures 00:12:22
Lecture 1 :
Content Optimization and Metrics
Hello and welcome to module 6 of the Automated Content Production and Algorithms course called – Content optimization and metrics. This module will cover; i. Content optimization, an overview ii. How publishers are augmenting the news dissemination iii. Methods and methodologies to enhance the spread of news iv. Tools to optimize the performance of content online Also as a reminder, after watching the videos, please proceed to read the three documents that are added to this module. They include; Know your algorithm; Social Media Platforms as News Publishers and Distributors; and Deepening Engagement for Lasting Impact. After this, please ensure you take the quiz.
Lecture 2 :
Content Optimization
Content optimization, an overview This is the practice of making sure that content is written in a way that it can reach the largest possible target audience. The process of optimizing includes ensuring that associated keywords are present, adding meta and title tags, and relevant links. This can also be the process in which a webpage and its content are optimized to become more attractive, useful and actionable to users. Data processing algorithms are increasingly applied to audience data with an eye toward expanding the monetizable audience by predicting and optimizing the performance of content based on historical patterns. News publishers are constantly tracking their audience to study their consumption pattern and gain insight into reader behavior towards delivery of a more custom stories. Audience analytics are a necessity in today’s newsrooms. Many newsrooms who take content optimization serious are following the data on their stories real-time. They have large flat-screen monitors projecting real-time metrics of the “trending” or “most read” stories. Insights garnered from these screens are used to create headlines, and content that they anticipate their audience want to see. A good example of this was a voter education and citizen engagement project I deployed in 2014 to 2105 for the general elections in Nigeria [Add link], except that this time, the process was in reserve.
Lecture 3 :
Content Optimization - Project EDAV
The project was called EDAV – Election Data Analytics and Visualization. The goal of the project was simple; find key data and information that is relevant to the electorates’ needs and make it easily accessible to them. To proceed I asked several questions; Who were the electorates? What issues and needs were most important to them? What conversation were these electorates having? Where were they communicating from? At what times or periods were they communicating? In seeking to understand who the electorates were, one would gain insight the demography of the audience. This piece of information many times show that the young, middle aged and the old all have different things they are particular about. It clearly defines the issues that each age group or gender finds more important. Studying the social conversations, interactions, behavioral pattern and sentiments of these different audience groups points to their concerns. This piece of information also leads you to individuals or organizations influencing the conversations, a key insight when optimizing your content. The devices used by your audience is a key metric. The way people interact with news on mobile devices is quite different than news behavior on the desktop/laptop computers. Data has shown that people spend far more time with news apps on the smartphone and tablet, visit more pages at a sitting, and return more frequently than they do on conventional computers. The time and periods where your audience is active, is key because you will not want to serve them content when they are asleep or serve them a particular content when they are interested in another.
Lecture 4 :
How Publishers are Augmenting the News Dissemination
How publishers are augmenting the news dissemination Top media organizations are waging a war on your attention to see who comes out tops. Buzzfeed for example has experience exponential growth in the past few years, not by advertising but by leveraging technology - A Headline Optimization Tool for split-testing headlines. This will be discussed in detail at the Tools section of this module. Headline is king.The Headline Optimization Tool I mentioned earlier uses a technique called A/B Headline Testing. This technique is used to determine the best headline for an articleusing some metric like the number of clicks on the story. Reporters while writing a story furnish it with a number ofother headlines. The news site displays those alternate versions of the headlines to different audience in order to study they click behavior. At a point, the monitoring algorithm will pull results together to show which of the alternate headlines was clicked the most. This method can also be used for video publications and images.
Lecture 5 :
Methodologies to Enhance the Spread of News
News outlets will not back down when it comes to finding ways to retain your attention. They will continue to invest in resources to produce methods to generate clicks. I will talk about some of them. Widgets: At the bottom of many articles, you will a number of other articles calling out to you. The algorithm used here has studied you clicks, your reading preference and history and serves you the content it feels you most likely will want. Question headlines: Evidence shows that headlines styled as questions lead to a different response compared to the traditional and forward-reference headlines, especially when paired with a topic the participants found particularly unappealing. Let’s take a look at these two headlines; “Breaking News: A spaceship has been spotted across Egypt” and “Breaking News: An UFO has been spotted flying past the pyramids in Egypt, do you think Aliens are coming?”. One would find that the reaction between both of them will be quite different. Thumbnails: Flashy thumbnails and headlines are mostly there to keep readers clicking. Publishers experiment with different thumbnail images. Many times the algorithm is random. Timeliness: Earlier I mentioned the time factor, which is key to not just creating a content that is timely, but knowing what time to publish it to your social media. This is so because your audience is interested in different things at different times.
Lecture 6 :
Tools to Enhance the Spread of News Online
Tools to optimize the performance of content online Newsrooms use a wide range of tools to harness data towards creating even better content. Some of them include; Echobox: This tool uses Artificial Intelligence to drive your social media activity. Its analytics feature collects and aggregates your social media data to help you discover which post performed best, what contents you should re-share. It also shows you what kind of content to recreate and the editors or channels that performed best. Keyhole: I used this tool in 2014 and ’15 for the EDAV project. At the time it was still free. Keyhole is a hashtag tracking software that measures keywords and hashtags metrics in real-time. Publishers can also use this to understand the sort of content they need to create. Chartbeat: This tool allows you see how your audience connects with your content in real time, adapts user experience and test page elements like headlines within your normal workflow, to know what moves your most valuable audience. NewsWhip: This tool tracks the spread of any content within seconds of publication, and predicts what will make an impact every day. It monitors trends, topics, formats, authors, publishers, social accounts, and posts across seven social platforms. Nelio A/B Testing: This is the tool I discussed about earlier used to create alternate headlines. Every news organization has different values, and what metric matters to them at one point or another. The trick is to measure everything, but focus on optimizing for one or two. It could be subscription rate, click rate, engagement, bounce rate or overall satisfaction. Metric will continue to be used towards optimizing, creating and distributing news content to push readers to ask for more of the content that they want. News organizations will continue to mine troves of data littered with behavioral traits, personal characteristics, sentiments and in some cases key words posted by users on social media towards the creation of the user-friendly premium content. In other words, you can't judge all content by the same yardstick or by the same metric. You have to think about what the content is supposed to do for your business or for your editorial strategy, and then measure the metric that helps you optimize for that. In the next video, we will discuss the core strength of algorithms in news under the module - Platform Power and Algorithms. That will be all for now
Lecture 7 :
Content Optimization and Metrics
Lecture 8 :
Content Optimization and Metrics
Lecture 9 :
Content Optimization and Metrics
Lecture 10 :
Quiz
Quiz

How do i access the course after purchase?
It's simple. When you sign up, you'll immediately have unlimited viewing of thousands of expert courses, paths to guide your learning, tools to measure your skills and hands-on resources like exercise files. There’s no limit on what you can learn and you can cancel at any time.
Are these video based online self-learning courses?
Yes. All of the courses comes with online video based lectures created by certified instructors. Instructors have crafted these courses with a blend of high quality interactive videos, lectures, quizzes & real world projects to give you an indepth knowledge about the topic.
Can i play & pause the course as per my convenience?
Yes absolutely & thats one of the advantage of self-paced courses. You can anytime pause or resume the course & come back & forth from one lecture to another lecture, play the videos mulitple times & so on.
How do i contact the instructor for any doubts or questions?
Most of these courses have general questions & answers already covered within the course lectures. However, if you need any further help from the instructor, you can use the inbuilt Chat with Instructor option to send a message to an instructor & they will reply you within 24 hours. You can ask as many questions as you want.
Do i need a pc to access the course or can i do it on mobile & tablet as well?
Brilliant question? Isn't it? You can access the courses on any device like PC, Mobile, Tablet & even on a smart tv. For mobile & a tablet you can download the Learnfly android or an iOS app. If mobile app is not available in your country, you can access the course directly by visting our website, its fully mobile friendly.
Do i get any certificate for the courses?
Yes. Once you complete any course on our platform along with provided assessments by the instructor, you will be eligble to get certificate of course completion.
For how long can i access my course on the platform?
You require an active subscription to access courses on our platform. If your subscription is active, you can access any course on our platform with no restrictions.
Is there any free trial?
Currently, we do not offer any free trial.
Can i cancel anytime?
Yes, you can cancel your subscription at any time. Your subscription will auto-renew until you cancel, but why would you want to?

Blaise Aboh,

97053 Course Views

3 Courses

Blaise Aboh is a Citizen Data Analyst and consultant and also the founder of AI Envoy Robotics. He is also lead partner at Orodata, a Civic Technology Organization studying and leveraging data-driven science and artificial intelligence to extract knowledge and insights from data. Blaise has equipped over 5000 media professionals with tools and technologies to practice better data science and data journalism in the past 4 years.