Speaker 1: Hello, and welcome to our video on Text Analysis in Mac. Discovering hidden patterns from unprocessed human language is the process of text analytics, which helps with prediction and decision making. The different aspects of decision making include topic modeling, classification, sentiment analysis etcetera. There are various real world applications to underlying causes of damages, repairs and work orders. The data comes from internal sources such as internal reports, maintenance logs, work orders and technical support cases. Text data can provide important information such as cause of equipment failure, pain points in products and process design and action recommendations based on historic data. In topic modeling, it can find topics in a collection of documents that reflect underlying patterns and relationships in the raw text data. In classification, it can classify documents into predetermined categories for efficient information retrieval and prediction. In summarization, an exact summary can be extracted from a set of data. This is done by the access of data from databases, the web and internal file repositories and explore by visualization. A common concept you may see in this analysis is the idea of a tokenized document. A tokenized document is a document represented as a collection of words also known as tokens which is used for text analysis. Use tokenized documents to detect complex tokens in text such as web addresses, emoticons, emoji and hashtags. The same requires an installation of text analytics toolbox. As we can see in our code here, cleaning up the data is also required before we can find the best outcome. We are using our very own blog on Twitter analysis for our example. The inclusion of punctuation symbols and words like and, the and to are not likely to add value. These low information words are called stop words. To clean this, we use commands like remove stop words. This is all a part of the word cloud arrangement. Text summarization now can be done using join and split sentences commands. The next outcome of all these commands is visualized in a model of predictive analysis and can be plotted to find the occurrence of different words. Do you want to see more such interesting stuff like this? Then check out our fun with MATLAB playlist where we keep showing some interesting topics for you. Do make sure to check out those videos and enroll in a free course on MATLAB fundamentals. Thank you for watching this video. Do like this video if you found it helpful. If you have any queries, post them in the comments or get in touch with us. Follow us on LinkedIn, Facebook and subscribe to our YouTube channel. Education is our future. MATLAB is our feature. Happy MATLABing.