What is natural language processing?

The definition of natural language processing can vary depending on the application and use cases. But as Jon Campbell from Moody’s Analytics’ NewsEdge defines it, NLP uses computers to analyze text.

The goal is to enrich news and textual data with additional signals such as industries, subjects, locations, essential people, sentiment, event classification, and news clustering.

This branch of artificial intelligence gives computers the ability to understand text and spoken words like humans. The deep learning NLP models enable computers to analyze human language and understand deeper contexts like intent or sentiment.

The Application of NLP Metadata Enrichment in Business

The application of artificial intelligence has become imperative in business, especially in recent years. A subset of AI, NLP now plays a critical role in organizational data management and analytics.

According to industry reports, the NLP market is expected to grow from the current USD 15.7 billion to USD 49.7 billion by 2027, at a CAGR (compound annual growth rate) of over 25%. Much of the growth is attributed to increasing demand for NLP solutions to streamline operations, drive productivity, improve customer experience, and automate mundane but critical business processes.

While there is a general wave of adoption across industries like retail, health care, logistics, the public sector, and manufacturing, the BFSI (Banking, Financial Services and Insurance) sector will be the largest adopter of NLP. BFSI firms are primarily driven by the need to mitigate risks through information retrieval, intent parsing, customer service, and compliance automation.

The North American region is expected to be the largest market due to rapid innovation and advancements of AI technologies in the area.

One of the leading NLP solutions in the market, NewsEdge has had the experience of working with multiple business categories seeking solutions for specific use cases. The user for such a platform could be a news publisher trying to categorize and tag its content or an algorithmic stock trading firm with high confidentiality standards that wants to run the software in-house.

Organizations can not only analyze externally published text content like news articles but also categorize their internal textual content, such as research reports and emails, instantly and at scale. The engine can extract context from unstructured data or text without manual reading, saving time and resources.

Steady demand, a series of custom projects, technology improvements, and the advent of the cloud led to the creation of the NewsEdge NLP Engine. It is now possible to analyze large amounts of content and derive business intelligence in minimal time.

Metadata Enrichment Through Natural Language Processing

Modern AI and ML advancements allow instant data processing and enrichment at scale. Analyzing digital records has made it possible to create beneficial NLP metadata enrichment pipelines such as sentiment, names, context, trends, and location. Using natural language processing to identify useful names, competitors, events, locations, and organizations within the textual records and correlating them with other sources can create meaningful insights and metrics.

The advanced capabilities benefit decision-makers by helping them identify trends, get timely alerts, and stay ahead of the curve.

Users can leverage NewsEdge news solutions to inform their decision-making or use the NewsEdge NLP Engine enrichment technology for their proprietary content processing. This is particularly relevant for any environment where an overwhelming amount of information is streaming continuously without the time and resources to parse the information in time to find what is important.

With over two decades of news processing experience, the NewsEdge team has developed a stable, easily explainable, rich source of metadata that users can rely on to feed their own applications and models with minimal latency.

A Variety of Business Use Cases

The NewEdge Feed Solution curates information from thousands of global sources. Newswires, press releases, newspapers, blogs, and websites provide comprehensive coverage of companies, industries, and events affecting the market for specific user types, like a trading platform. By enriching each story with metadata such as entity, subject, industry, sentiment, trading impact, and event codes, The NLP enrichment engine provides users with timely insight into news and events impacting investment strategies.‍

Similarly, another example of natural language processing with the platform is the ability to combine two disparate information sources, like news articles from the public domain and internal emails to create relevant business information for the enterprise.

A news story’s entity extraction and categorization highlight data such as

competitor information, locations, relevant topics, and geopolitical events. The story in the public domain is followed up with an internal email from someone who has insight into the topic. Processing the news and the email in a combined manner leads to exciting and actionable results.

About Jon Campbell:

Jon Campbell is the Head of Library Science for the Media Solutions team within Moody’s Analytics. He leads news data enrichment efforts centered around using natural language processing (NLP), artificial intelligence (AI), and machine learning (ML) to generate news-derived insights. Throughout his career, Campbell has focused on using news and other text-based information to generate meaningful intelligence for business decision-making.

Campbell has been involved in news aggregation and value-added metadata markup since 2000. He was an early contributor to dot-com pioneer ScreamingMedia and held information management positions in Liz Claiborne Corporation, Williams-Sonoma and Restoration Hardware. He joined Moody’s Analytics as part of its acquisition of Acquire Media, a leader in real-time news solutions.

Campbell holds a Master of Arts from the University of Virginia and a Master of Legal Studies from Rutgers University.