Course Number: OMIS Instructor: Dr. Akshay Bhagwatwar Course Title: Social Media Analytics Semester: Fall 2016 Classroom: Barsema Hall xxx Credit Value: 3 Class Hours: Office: Barsema Hall 328P Office Hours: Office Phone: (815)753-6380 Email: abhagwatwar@niu.edu COURSE DESCRIPTION This course is designed to help students continue to build skills and knowledge about data analytics on consumer oriented (Twitter, Facebook) and enterprise social media (Yammer, Chatter, Jive Software). This course will provide students with a thorough understanding of the role data analytics on such social media platforms can play in driving organizational decision making. As part of the course, students will develop knowledge of how organizations are currently using the data generated via social media platforms, learn industry tools that help extract and analyze the data, and visualization techniques that help present the results of the analyses to stakeholders. During the semester, projects, assignments, and hands-on exercises uses that afford the student the opportunity to work through many real-life business situations and analyze data generated from real-world social media platforms. OBJECTIVE: At the completion of the course, students will be able to: Understand how data generated via social platforms drives decision making in organizations Learn how organizations are replacing traditional collaboration platforms with the emerging enterprise social media platforms Understand techniques related to data extraction/mining on popular social media platforms Analyze the data using tools such as Tableau and SAP Lumira Report on the results of their data analysis using different visualization techniques SAP Lumira and Tableau solutions are popular industry tools used for data analytics and visualization. The hands-on exercises, coupled with the in-class discussions on social media analytics, will prepare the student with the knowledge sought by businesses looking to use data analytics to maintain their competitive edge in the market place and drive business decision making. REQUIRED TEXTBOOK: Mining the Social Web: Data Mining Facebook, Twitter, LinkedIn, Google+, GitHub, and More by Mathew A. Russell
CLASS SCHEDULE: Class Topic Reading Week 1. Week 2. Week 3. Course Overview Overview of Social Media Platforms and Enterprise Social Media Systems & Functionality Introduction to Yammer and creating a Yammer account Social media analytics for the business Value of Data analytics in social media Understanding the big data problems Role of data visualization Understanding Tableau for business Tableau tutorial Data analytics using tableau (1) MIS Quarterly Executive: The impact of social media on C- level roles (2) HBR: Analytics 3.0 By Thomas Devenport (3) Business Analytics: Why now and what next? (1) IBM analytics: Gaining business value from social media (2) IBM analytics: Customer analytics in the age of social media (3) IBM analytics: Making customer insights actionable (4) Dell case study Handouts on Tableau and tutorial documentation Week 4. Understanding a social network Nodes in a social network Strong and weak ties Mapping the social network Week 5. Data scraping and cleansing part 1 Data scraping on Twitter Managing the twitter API Handouts on social network analyses Russell: Chapter 1 Week 6 Data management using Datasift and Tableau DataSift and Tableau handouts Week 6. Data scraping and cleansing part 2 Data scraping on Facebook Exploring the Social Graph API Russell: Chapter 2 Week 7 Data management in social media Data cleansing Data clustering using LinkedIn/Twitter data Russell: Chapter 3 Week 7. Data analyses techniques for social media part 1 Structured and unstructured data Text analytics and text parsing Text analytics using Tableau Handouts
Class Topic Reading Week 8. Guest Speakers Week 9 Project idea presentations Week 10. Data analyses techniques for social media part 2 Opinion mining and sentiment analyses Week 11. Data analyses techniques for social media part 3 Opinion mining and sentiment analyses Hands on exercise with Twitter data sets Week 12. Social data in motion Word associations Creating tag cloud visualization Graphs Interactive maps Sentiment analysis and opinion mining book chapter, Bing Liu Sentiment analysis and opinion mining book chapter, Bing Liu Twitter data sets Week 13. Introduction to SAP Lumira Understanding data on Lumira Data management on Lumira Lumira visualization techniques SAP Lumira handouts and visualization manual Week 14. Hands-on exercises with SAP Lumira SAP Lumira handouts and visualization manual Week 15. Final Project Presentations Week 16. Final Exam GRADING: Grading will be on a straight scale (as opposed to a class curve/average). Final grades will be based upon the total percentage earned. 93% and above A 90% - 93% (not including 93%) A- 87% - 90% (not including 90%) B+ 83% - 87% (not including 87%) B 80% - 83% (not including 83%) B- 77% - 80% (not including 80%) C+ Grades will be calculated by weighing the following work as described here:
Class Project 40% Project Presentation 10% Class Participation 10% Homework Assignments 20% Final Exam 20% 100% MAKING UP A EXAM: Typically make-ups are not allowed if the instructor does not approve an excused absence for the student in advance. Exams cannot be made-up if timely prior permission of instructor has not been obtained, and/or if appropriate documentation is not provided. If a student is unable to attend a class session, it is the student's responsibility to acquire the class notes, assignments, announcements, etc. from a classmate. Initiating the request for any make-up in a timely manner is the student s responsibility. OMIS ATTENDANCE POLICY The OM&IS Department believes that student academic success is enhanced by good classroom attendance. The following Attendance Policy was developed in an effort to be consistent and to inform students of the attendance expectation in the department. 1. Students not in attendance at the start of class time will be counted late (0.5 absent). 2. Penalties for non-attendance are as follows: Courses with One Class Periods per Week NUMBER OF ABSENCES PENALTY 0-2 absences No penalty 3-4 absences 1 course letter grade reduction 5-6 absences 2 course letter grade reduction 7-8 absences 3 course letter grade reduction 9 or more absences Automatic failure in the course 3. No missed exams, quizzes, or other in-class assignments, announced or unannounced, can be made up at a later date. Students missing class sessions in which exams, quizzes, or other assignments occur will receive the grade of zero for the missed work. It is the instructor s sole discretion to either permit or not permit students to complete special make-up assignments prior to the class session(s) in which work will be missed. The sole exception to this is the case of an emergency absence, for which the student will be allowed to make up the missed work if the student so requests within one week of the absence. Students failing to request to make up the missed work within one week after the absence will receive a grade of zero for the missed work. 4. Students may request an emergency absence for the following reasons: a. illness or medical emergencies b. death in the family 5. Emergency absence requests must be in writing to the department chair within one week of the emergency absence and be accompanied with appropriate documentation explaining the reason for the absence, e.g., physician letter, newspaper obituary notice, etc. The
instructor will notify the student of the decision made regarding the emergency absence request. Students are advised to plan and use their allotted non-penalty absences wisely. Employment interviews should be scheduled outside of class time, as they are not acceptable reasons for approved absences! STUDENT CONDUCT AND ACADEMIC HONESTY: Students are expected to uphold the NIU standard of conduct for students relating to academic honesty. Academic honesty is defined as an intentional act of deception in which a student seeks to claim credit for the work or effort of another person or uses unauthorized materials or fabricated information in any academic work. The penalty for academic dishonesty is severe. Any student guilty of academic dishonesty may be subject to receive a failing grade for the exam, assignment, quiz, or class participation exercise as deemed appropriate by the instructor. Any student guilty of academic dishonesty could be subject to receive a failing grade for the course and can expect to be reported to the appropriate officials in COB and appropriate University Officials. If a student is unclear about whether a particular situation may constitute academic dishonesty, the student should meet with the instructor to discuss the situation. Students assume full responsibility for the content and integrity of the academic work they submit. The guiding principle of academic integrity is that a student's submitted work, examinations, reports, and projects must be that student's own work for individual assignments, and the group's own work for group assignments/projects. Students are guilty of academic dishonesty if they: Use or obtain unauthorized materials or assistance in any academic work; i.e., cheating. Falsify or invent any information regarded as cheating by the instructor; i.e., fabrication. Give unauthorized assistance to other students; i.e., assisting in dishonesty. Represent the work of others as their own; i.e., plagiarism. Modify, without instructor approval, an examination, paper, record or report for the purpose of obtaining additional credit; i.e., tampering Students are expected to uphold the NIU standard of student conduct. Please refer to: http://www.niu.edu/communitystandards/student_code_of_conduct/index.shtml for details on student conduct and academic dishonesty. Ensure that you talk to the instructor if you have any questions about the above two important issues. The instructor reserves the right to use resources to help detect cheating incidences.