Sentiment Analysis

Monitor early signals and catch subtle shifts in language tone to drive insightful insights

• How Sentiment is Calculated
• Sentiment in Event Transcripts
• View and Compare Company Sentiment in Company Profile

With AlphaSense, you can use AI-based Sentiment analysis to identify, quantify, and analyze levels of emotion within text. Understanding sentiment can help investors and business professionals catch the subtle inflection points in language that move markets and provide early indicators of shifting corporate performance.

How Sentiment is Calculated

Calculating sentiment for a specific document first entails counting the raw inputs. That includes counting

• Total negative statements in the document
• Total positive statements in the document
• Total statements in the document

The raw inputs drive the raw sentiment score for a document. Raw sentiment is the percent of the document that is positive minus the percent that is negative.

From there, the model calculates a normalized sentiment score. The normalized sentiment is the raw score normalized across all companies such that the mean sentiment is 0 and the scores are stretched between -99 and 99. This score matches what you see in the AlphaSense platform.

Each sentence in a transcript gets a prediction of positive, negative or neutral along with a confidence value (e.g. 99% confidence this statement is positive). Our sentiment model, which has been trained on a huge body of financial documents, first forms a contextual understanding of each sentence based on the surrounding context and what’s important in that sentence or paragraph, and then uses it to make a sentence level prediction and output a confidence value based on how confident our model is in its prediction. The model also highlights important phrases and sentences that are driving its predictions, generating a summary for our users.

For the doc level score we take the count of positive statements minus the count of negative statements divided by the total number of statements.

We then normalize these scores by:

• The confidence of each prediction
• The mean and standard deviation of scores across all transcripts in the last 2 years such that the average score is 0.

Some examples of what this means:

• A score of 0 is average across all transcripts
• A score of 40 (or -40) is in the top 20% (or bottom 20%) of all transcripts
• A score of 99 (or -99) is in the top 2% (or bottom 2%) of all transcripts

Sentiment in Event Transcripts

Use Event Transcripts to analyze key inflection points during Earning Calls to spot postive and negatives. 

This helps you:

• Track sentiment changes within a single call.
• Compare a company’s sentiment over time on key topics and trends.

To view Sentiment in Event Transcripts, narrow your Sources to Event Transcripts Only on your desired company or watchlist.

To Get Started:

• Go to Document Search.

• Enable Event Transcripts:

  • In the Quick Filters section, turn on Event Transcripts under Company Documents.

• Search for a Transcript:

  • In the Keyword search bar, enter a relevant keyword.

  • In the Company/Ticker search bar, type the name of the company.

  • Select a Transcript from the search results.

• Review the Transcript:

  • Scroll through the transcript.

  • Look for red underlines (negative sentiment) and green underlines (positive sentiment) to identify key insights.

Optional:

• To hide sentiment markers, select the “Hide Sentiment” button at the top of the page.

View and Compare Company Sentiment in Company Profile

To view the sentiment score for a specific earnings call, go to the company profile and look for the sentiment score in the Earnings Call Sentiment section. The sentiment score is calculated by counting the total positive, negative, and neutral statements in the document, then normalizing the score across all companies. You can also search for specific keywords in the earnings call transcript to see positive or negative sentiment markers.

This helps you:

• Track sentiment changes within a company.
• Compare a company’s sentiment with competitors, peers, and industry leaders.

To Get Started:

• Go to Document Search.
• Enter the company’s name in the Company/Ticker search bar.
• Scroll to find the Earnings Call Sentiment section.

To Compare with Other Companies

• In the Add Public Companies bar, enter the name of a competitor or peer company not already listed.
• Click Add.

Expert Tip: Click Export Data to Excel to download historical sentiment data to Excel for offline analysis.