People, Sentiment and Social Network Analytics with Excel
Author | : Mong Shen Ng |
Publisher | : |
Total Pages | : 501 |
Release | : 2019-06-23 |
ISBN-10 | : 1075419514 |
ISBN-13 | : 9781075419515 |
Rating | : 4/5 (515 Downloads) |
Download or read book People, Sentiment and Social Network Analytics with Excel written by Mong Shen Ng and published by . This book was released on 2019-06-23 with total page 501 pages. Available in PDF, EPUB and Kindle. Book excerpt: A lot of organizational data is often untapped unstructured data in the form of text & numbers. This is the only book that teaches you how to use Excel & Word for People Analytics, Text Analytics, Sentiment Analysis & Social Network Analysis with step-by-step print-screen instructions: 1) Text Analytics (Text Mining): Mine employee's resume, engagement surveys & Glassdoor comments to uncover insights, then visualize the comments using "Pro word cloud", a free Microsoft Word add-In. 2) Sentiment Analysis: Mine text from social network posts & Glassdoor comments, then run Sentiment Analysis using "Azure Machine", a free Excel add-In. Learn how to predict a company's average employee attrition rate. E.g. a company's average employee attrition rate is predicted to be 8.1%, if unemployment rate is 3.3%, GDP growth is 2.3% & its Glassdoor public sentiment rating is 5. 3) Social Network Analysis (SNA) & Organizational Network Analysis (ONA): Run SNA & ONA using "NodeXL", a free open-source Excel network analysis tool. Learn how to convert an employee's social network into a score, & then predict their performance rating. E.g. an employee is predicted to get a performance rating of "7", if their "Social Network Size" is 16, "Social Network Diversity Index" is 3.1 & "Skillsets Score" is 8. 4) Predictive People Analytics: Use Excel's Statistical Analysis tools (Decision trees, Correlation, Multiple & Logistic Regression) to run Predictive People Analytics covering: Employee Engagement, Employee Attrition & Absenteeism, Performance, Compensation & Benefits, Training & Development, Health, Safety & Environment, Diversity & Inclusion. For example, an employee is predicted to have a 60% probability of getting into accidents, if he is age 30, worked 2 years in the company, and took 6 days sick leave. An employee is predicted to get rated "7" for Customer Service, if the training program that they attended has a training evaluation score of "8".