SAS Visual Text Analytics.The purpose of this assignment is to use SAS Visual Text Analytics to analyse a dataset labelled AmazonAlexaReviews available on Moodle as a CSV file.
The purpose of this assignment is to use SAS Visual Text Analytics to analyse a dataset labelled AmazonAlexaReviews available on Moodle as a CSV file.
The dataset consists of 3151 Amazon verified customer reviews of various amazon Alexa products like Alexa Echo, Echo dots, Alexa Firesticks etc. The data also includes star ratings, date of review, and variants of Alexa products. In this assignment, you will use only the customer reviews text, which is named verified_reviews. The verified_reviews variable represents free-form, unstructured customer reviews collected from Amazon’s website.
You are required to conduct a data analysis of Amazon verified customer reviews using SAS Visual Text Analytics in two parts. Part 1 consists of exploring predefined concepts and automatically generated topics to derive insights from the data. Part 2 consists of defining your own custom concepts and custom categories to answer specific research questions.
SAS Visual Text Analytics in SAS Viya is a web-based text analytics application that uses context to provide a comprehensive solution to the challenge of identifying and categorizing key textual data. In SAS Visual Text Analytics, you can use the following analysis nodes to build and automate models (based on training documents):
You can then customize your models in order to realize the value of your text-based data.
SAS Visual Text Analytics in SAS Viya combines the visual programming flow of SAS Text Miner with the rules-based linguistic methods of categorization and concept extraction in SAS Contextual Analysis. These capabilities, along with document-level scoring for each component, are combined in a single user interface.
Using SAS Visual Text Analytics in SAS Viya, you can identify key textual data in your document collections, build concept and categorization models, and remove meaningless textual data.
By default, words that provide little or no informational value (stop words) are excluded from topic analysis. A default stop list is included and automatically applied for all supported languages. Examples of stop words in English include the articles a, an, and the and conjunctions such as and, or, and but. Other terms that are specific to your document collection but provide little or no value due to their low frequency are also identified and excluded. For more information about stop lists, see Text Mining Action Set: Details in SAS Visual Text Analytics 8.5: Programming Guide.
SAS Visual Text Analytics provides a number of text analysis nodes that are arranged in a sequence that you control. This sequence takes the form of a pipeline, which empowers you to analyze your document collection with considerable flexibility. When you run a pipeline, the following analyses are performed on data in your project:
For more information about categories, see Categories.
The models that are generated for Concepts, Sentiment, Topics, and Categories can then be deployed, and used to automate the process of labeling input documents. You can also register your models, which allows for model governance and model change control over time. For more information about registering models, see Registering Models.