Sentiment Analysis is one of the most important and popular applications of Natural Language Processing. Sentiment Analysis is a process of extracting the opinion of a person towards a specific topic from texts. According to Wikipedia

Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information.

By using Sentiment Analysis, we can extract subjective information from texts. It can help businesses to increase engagement with their customers, analyzing feedbacks, etc.

With modern Deep Learning algorithms, the ability to understand the sentiment of texts has increased exponentially. Algorithms like LSTM Network can perform Sentiment Analysis with amazing accuracy.

How Sentiment Analysis work?

First, we need to understand, that Sentiment Analysis is a Supervised Machine Learning problem. In other words, in Sentiment Analysis, our algorithm learns a mapping between the text and sentiment. The sentiment can be Positive, Negative, and Neutral. In some cases, we work only with Positive and Negative sentiment also.

As it is a Supervised Classification problem, we need a Classification algorithm. A Classification algorithm classifies inputs to specific classes. In this case, the input is the text from various sources and output classes are the possible sentiments.

All Machine Learning algorithms work only with Numbers. But text information is string, not numbers. That means we need some way to represent these texts into numbers. To do that, we use Word Embeddings.

Word Embedding algorithms are algorithms that represent the texts into numbers without losing the meaning of the text and the order of the words in the sentences. Word2Vec and GloVe are some examples of Word Embedding algorithm.

Text is a type of Sequenced Data. In Sequence Data, the data comes as a sequence. In this case, it is a sequence of words.

To process these sequence data, we usually use Recurrent Neural Networks. LSTM is a type of Recurrent Neural Network that works better than other types of Recurrent Neural Networks and has some other advantages also. LSTM can perform Sentiment Analysis with amazing accuracy.

Applications of Sentiment Analysis

Sentiment Analysis is one of the most widely used technique in Data Analysis. It is very important and various industries are dependent on it.
There are so many applications of Sentiment Analysis. Some of them are discussed below.

Customer Engagement

Customer Engagement is one of the most important way to attract potential customers. Various businesses do different things to increase engagement with customers. Unfortunately, they don’t work that well.

Sentiment Analysis can play a very important role in increasing engagement with customers.

For example, these days companies receive thousands of posts through various Social Networking platforms. People use these platforms to tell their experience with a specific product/service, ask questions, etc. Using Sentiment Analysis businesses can analyze these posts on a very large scale and take specific actions. By taking specific actions businesses can increase customer engagement easily.

Decision Making

Another application of Sentiment Analysis is that it helps the management team of a business to make decisions that are beneficial to the company.

Sentiment Analysis can be used to extract the opinion of a large group of peoples towards a specific topic. By extracting the opinion, companies can understand the demands of people. Based on public demand, they can make changes to the business.

Sentiment Analysis can also be used in detecting trending topics. By detecting the trending topics, the management can plan for the future of the business. For example, based on new trends, a clothing company can make specific changes in their products to meet customer expectations.

Competitive Business

There are multiple companies that provide the same products or services. Because of that companies face massive competitions. They have to compete with companies. For example, there are so many companies that make mobile phones. That means customers have so many choices.

Sentiment Analysis can be useful in such scenarios. For example, getting x% positive and y% negative reviews on a certain product doesn’t make that much sense unless we compare the result with other results from other companies. By doing that we can understand how well a particular business is doing over its competitors.

Employee Engagement

Maintaining a good relationship with employees is very important for businesses. But in large corporations, with thousands of employees, maintaining it is very hard.

Employee Feedbacks are very important and useful in understanding the employees, their problems, etc. But as there are so many feedbacks, process all these feedbacks is very hard and challenging.

Sentiment Analysis can make this process very simple and fast. We can use Sentiment Analysis to analyze all the feedback and comments.


There are so many applications of Sentiment Analysis. It is widely used in numerous industries. In businesses, Sentiment Analysis can be used in various situations and they can greatly affect the performance of the businesses.

According to Wikipedia, “React (also known as React.js or ReactJS) is a JavaScript library for building user interfaces. It is maintained by Facebook and a community of individual developers and companies.

React can be used as a base in the development of single-page or mobile applications, as it’s optimal only for its intended use of being the quickest method to fetch rapidly changing data that needs to be recorded. However, fetching data is only the beginning of what happens on a web page, which is why complex React applications usually require the use of additional libraries for state management, routing, and interaction with an API.”

According to Wikipedia, “Angular (commonly referred to as “Angular 2+” or “Angular v2 and above”) is a TypeScript-based open-source web application framework led by the Angular Team at Google and by a community of individuals and corporations. Angular is a complete rewrite from the same team that built AngularJS.”

According to Stack Overflow Developer Survey 2018, the front-end framework, Angular, is used by 36.9% of software developers for creating user interface.


In the modern age, data analysis has crept up to the top of the Digital Transformation paradigm and Data Analyst is becoming one of the most important roles in the industry as they are involved in key business decisions and strategies because of their insights and reporting capabilities.

But what is Data Analysis? In simple words, Data Analysis is a process of extracting useful information from data using different Statistical and Mathematical methods. But Data Analysis alone cannot help. It is because after performing Data Analysis on some data, we usually store the information in CSV file, some databases, or in some other format and it is very difficult to read data from these formats, especially for non-technical people. Also, it is very unintuitive to read data from those files. To solve this problem, we perform Data Visualization. Data Visualization is the presentation of data in pictorial and graphical format. These pictorial and graphical formats are very easy to understand for even non-technical people.

To prove this point, let’s assume an excel sheet having thousands of rows of sales data. Now let’s say we just look at the data for 30 seconds, then someone asks a question like which product is giving maximum profit or which product is giving minimum profit, it will be very difficult to provide him with a satisfactory response as it is hard to get this type of information from those data just by looking at it.


Today in the digital age, everyone has access to gadgets like a mobile phone or a professional camera that can take a picture or record audio and video of different types of incidents, events etc. that occur in our life. There are so many online platforms like YouTube, Instagram etc. where we share these types of files. Just imagine the amount of data we are talking about and all kinds of meaningful information we can extract out of these through proper analytical tools. To perform Data Analysis, it is important to understand that these recorded images, videos, or audios are very complex and unstructured. But there are tools available by which we can perform the analytics to extract information from these types of data

Problem Actualization

According to the requirement of the client, the analysis tool that we have built needed to have the ability to analyze these data and extract meaningful information from these data. They wanted a system to upload different images, pdf documents, audio files, and video files to the system for analysis.

For images and pdf documents, the client wanted the textual information from those files. That means they needed an OCR system.
According to Wikipedia
“Optical character recognition or optical character reader, often abbreviated as OCR, is the mechanical or electronic conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo) or from subtitle text superimposed on an image (for example from a television broadcast).”


Let’s assume that we want to analyze how people think about a specific topic or maybe how they react to a certain incident, or what are their opinions about a particular topic.

For this, we can use different Machine Learning and Deep Learning algorithms. For the purpose of analysis, first, we need data- data about the people, their opinions, their ideas etc. But where do we avail those data from?

Well, the answer is Social Networking Platforms like Facebook, Twitter, Instagram etc. Social Networking platforms are used by billions of people these days. Nowadays it is a part of our day to day life. We spend a huge amount of time on Social Networks and also share our personal moments on social networks. In other words, we generate a lot of data on those platforms. Now just imagine the amount of information those social networking sites have about us. They know everything about us. If we can perform any kind of logical analysis on those data, we can understand these people.

In Data Analysis, the first step is to aggregate data. Without proper data, we cannot do any analysis. In different cases, the sources of the data are different and the process of aggregating them is different too. In this case, we want to aggregate data from various social media networks, which means we need a Social Network Aggregator.

Social Network Aggregation is a process by which we collect data from various social networks like Facebook, Instagram, Twitter etc. for various analysis and other tasks. Basically, social network aggregator is a tool that has a social network aggregation process for collecting data.


Today in the digital age, we spend a lot of time on social networks. We share a lot of our personal moments on various social networks. Whether we are traveling to an adventurous location or having dinner in an exotic restaurant, we share those moments and emotions on social networks. Not only that, we also share our opinions and views towards a specific topic on social networks.

Just imagine the amount of information, these social networks have. They know everything about us including what we love, what we hate, where we live, our friends, interests etc. Now just think about what would happen if we build a platform where we can analyze these data and begin to understand what millions of people like or hate, what they are talking about, their opinions etc. For example, let’s say a company just launched a new B2C product and wants to know what the public is thinking about their product. With the ever-increasing abundance of data from various social networks, they can do it. What they need is a proper analysis tool.

API’s play a very important role in how our application will run and documenting the API’s in a format that everyone in the organization can understand as what is happening in the application. We will discuss one of the most used API documenting specifications called OpenAPI specifications.
OpenAPI specification is a language agnostic format which is used to describe RESTful web services. The resulting files can be interpreted by applications to generate code, produce documentation and create virtual simulations of the services they describe.
Let’s understand the OpenAPI specification with a example API document that describes the API service that allow us to retrieve list of users.

Data preprocessing is one of the most important steps in Machine Learning. This step cannot be avoided especially if data is in unstructured form. In this post, I’ll discuss the different steps using Scikit-Learn and Pandas.

“I’m assuming that you have some basic knowledge of Numpy and Pandas. If you don’t know Numpy and Pandas then first learn these topics.”