3 ways you can use NLP to uncover quantitative insights



October 5, 2021

How NLP Helps Quantify Research
How NLP Helps Quantify Research

Living in the information age, we adapt to a newfound need to prioritize an ever-growing information flow. The constant stream of news, research, blogs, tweets, and more contains insights into macroeconomic trends, how markets change over time, and even how companies perceive and adapt to their environment.

While reading, aggregating, and analyzing millions of pages of text is an impossible task for humans, innovations in the field of natural language processing (NLP) empower us to identify trends and perceive tone at scale. Data is treated as a corporate asset. The ability to sift through it all and identify the most relevant insights for your company has become a competitive advantage.

As we think about how these new technologies can help give companies and investors alike a competitive edge by uncovering the insights and trends hidden within millions of pages of text, let’s dive into three examples of how NLP can help you quantify human language and why that matters in your research process.

1. Validate C-suite interest on a trend

Investors and enterprise businesses across every industry use AlphaSense to help them make more informed decisions. One of the most common ways that teams use the AlphaSense platform to aid in their research is to assess how a trend changes over time. For example, let’s take a recent analysis by SAP, which looked at AlphaSense data to test their thesis that digitally mature companies perform higher than their peers.

To test their thesis, they wanted to understand how the C-Suite was thinking about digital maturity and business performance topics, including cash conversion cycle and digital technologies. So the SAP team turned to AlphaSense to identify a trend line over time by looking at the mention count of these topics within transcripts. They uncovered that the mention count increased overtime for three out of four of the KPIs they measured, validating that the C-Suite’s interest in these topics is growing.

SAP: Companies Going Digital Are Running Their Best

Leveraging mention count can help you build a more effective strategy, validate a thesis, or even combat tailwinds or ride the tailwinds of a trend.

2. Understand how different industries, geographies, or companies are thinking about a topic

In addition to time-based insights that help uncover how trends change over time, teams use the AlphaSense platform to understand how different industries or geographical regions are thinking about a specific topic. For example, Reuters recently leveraged AlphaSense to know how European companies are approaching buybacks.

Their analysis applied a simple filter in AlphaSense that limited their results to European-headquartered companies. As a result, they uncovered 800+ mentions of buybacks on earnings calls from European companies this quarter, a significant increase over last. Taking this analysis a step further, the Search Summary reveals the mention count per country, further deepening the potential insights from this search. In addition, to mention count per country, the Search Summary also shows the top industries and companies within the search results, providing additional views of the landscape.

European Buybacks Q2/Q3 2021

AlphaSense Search Link: European Buybacks Mentions on Earnings Calls

Search Summary is a powerful tool to help you gain an understanding of the landscape. Insights into major players, key industries, and geographies are all revealed to help you generate new ideas and explore questions more deeply.

3. Uncover tone at scale

So far, we’ve showcased how companies are using AlphaSense to synthesize and quantify millions of pages of text, focusing on the mention count of a trend or topic over time or by industry, geography, or company. The last example takes inspiration from many broker research partners who use AlphaSense’s sentiment analysis to identify the tone surrounding a topic or theme.

Conducting a sentiment analysis is simple within AlphaSense – all you need to do is add the word “positive” or “negative” to your search parameters. This type of search will return the documents that contain either positive or negative mentions about your topic of interest. In this example, we can see that the context in which companies are speaking about inflation is mainly negative, buybacks are primarily positive, and the economy is mixed.

Q2 Earnings Topics By Sentiment Heatmap

Percentage of Topic Mentions by Sentiment on Q2 2021 Earnings Calls

Understanding the context around a topic or theme can be particularly useful when understanding the areas of strength and weakness of a competitor or M & M&A target.

From millions of pages of unstructured text documents to clear and concise insights presented in bar graphs, pie charts, and heat maps, AlphaSense empowers business professionals to uncover hidden insights within the human language and ultimately make better business decisions.

Curious to see the searches powering these powerful insights? Sign up for a free trial today or check out a list of curated, pre-built searches in our Search Library.

Share this article

More like this