Over the last several decades, Computer Science has gained significant traction within the realms of finance and economics. Leading financial institutions are depending on computers to produce outcomes. For instance, JP Morgan, Chase, and Barclays utilize supercomputers to assess a stock portfolio’s risk or forecast an asset’s future worth. How is this accomplished?

In this piece, I will delve into how computers evaluate sentiment and leverage [machine learning](https://www.sas.com/en_us/insights/analytics/machine-learning.html#:~:text=Machine%20learning%20is%20a%20method,decisions%20with%20minimal%20human%20intervention.) to enhance investment returns.

## Sentiment Analysis

The investment landscape has transitioned from decision-making based on intuition to placing faith in computer programs. The era of traders energetically buying and selling stocks on the [trading floor](https://www.investopedia.com/terms/t/trading_floor.asp) is diminishing. Replacing floor traders are quantitative analysts, commonly known as quants. Quants design computer algorithms that heavily focus on mathematics to carry out trades and predict future stock performance.

Acknowledge the change in the market, [Dow Jones](https://www.investopedia.com/ask/answers/who-or-what-is-dow-jones/) has created a lexicon that enables computers to easily interpret potential stock movements. Another term for lexicon is *dictionary*. The Dow Jones Lexicon (DJL) compiles financial news and translates it into a format comprehensible to computers. Additionally, the DJL consists of six distinct dictionaries, all developed by Bill McDonald, a finance professor at the University of Notre Dame. However, financial firms also have the option to develop their own dictionaries tailored to their unique requirements.

When a computer is equipped with a lexicon, it can distinguish between positive and negative news. This subsequently informs traders about the prudence of executing a trade for that stock.

Below is a graphic illustrating whether sentiment for a stock is bullish (positive) or bearish (negative).

Let’s analyze a news article to scrutinize how the sentiment lexicon functions. [This](https://www.cnbc.com/2021/11/26/stock-futures-open-to-close-market-news.html) article from CNBC was published on November 26, 2021, shortly after scientists in South Africa unveiled a new variant of COVID.

*CNBC*

This is the introductory line of the article. You will see that one of the first words is “dropped.” A computer examining this snippet of text would classify it into the negative category and reduce the sentiment score, indicating that the stock market is bearish. Nevertheless, the positioning of the word is also crucial. Keywords located in headlines or the initial lines carry more significance regarding the sentiment score than if they were hidden within the text.

*CNBC*

In this screenshot, you will identify keywords such as, “down,” “dropped,” “lost,” and “fell.” Once more, these are terms that the computer will interpret as negative, thus lowering the sentiment score.

So, what does this process look like on the computer side? It actually stems from a fairly straightforward procedure. Crafting a sentiment analysis program is accomplished through the use of XML code. XML, which stands for extensible markup language, is closely related to HTML; however, it is not a standalone language. HTML specifies how a document should be presented, while XML defines the data contained within the document. For instance, in HTML, tags are inserted by programmers to create specific objects. For example, the `

` tag designates a heading on a website (h for heading; 1 for the first heading). Conversely, XML allows a programmer to refine their code further. Instead of using a broadly defined `

` tag, XML enables the programmer to name the tag as something like “ to clarify what is being defined. This customization simplifies code interpretation and addresses a business’s requirements.

Note: the following code was compiled by sqlauthority.com

“`xml

White
Blue
Black
Green
Red

Apple
Pineapple
Grapes
Melon

“`

In the example above, quants or traders would adhere to a similar structure as shown above, merely altering the tags to fit an algorithm designated for sentiment analysis.

Sentiment analysis merely scratched the