20543 - SOCIAL MEDIA MARKETING
Department of Marketing
Course taught in English
Course Director:
GAIA RUBERA
GAIA RUBERA
Mission & Content Summary
MISSION
Nowadays, Big Data freely available on social networks enables managers to perform traditional marketing analyses much more efficiently, rapidly, and pervasively than in the past. However, the recent cases of Cambridge Analytica and social bots also clearly show the drawbacks of combining Big Data with Machine Learning algorithms.
Given this new scenario, and in order to prepare students to face the new challenges of the Data Economy, this course introduces students to Python, one of the main programming language currently used in the Computer Science field. It also takes an in-depth look at social networks, with a specific emphasis on Twitter. Students learn how to collect real-time Twitter data through the use of an Application Program Interface (API) and how to conduct traditional marketing research and text analyses with this data.
Besides providing students with practical skills on how to collect and analyze data, the course discusses the risks of the Data Economy, with a particular emphasis on how Machine Learning algorithms can be used to influence individuals' decisions.
CONTENT SUMMARY
The course is divided into 4 main blocks that cover the following topics:
- Introduction to Python syntax.
- Twitter APIs and Marketing Analytics with Python.
- Database management and introduction to text analysis with Python.
- Machine Learning applications to marketing topics.
Intended Learning Outcomes (ILO)
KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
- Summarize and describe any dataset with Python.
- Describe the strenght and weakeness of any brand / organization using Twitter data.
- Explain how Machine Learning algorithms can be used to influence individuals' decisions.
APPLYING KNOWLEDGE AND UNDERSTANDING
At the end of the course student will be able to...
- Express basic programming commands in Python language.
- Collect any type of freely data available on Twitter.
- Estimate the competitive positioning of different brands according to Twitter data.
- Summarize and describe any dataset with Python.
Teaching methods
- Face-to-face lectures
- Guest speaker's talks (in class or in distance)
- Exercises (exercises, database, software etc.)
- Individual assignments
- Group assignments
DETAILS
During the course, in addition to face-to-face lectures, the following activities are completed:
- Guest speakers in class by managers working in the social media marketing area. These talks allow students to understand how multinationals are using data from social networks, and in particular Twitter, to conduct marketing analyses.
- Practice sessions to apply the knowledge acquired in class to specific marketing problems.
- Weekly, individual assignments to review the main Python codes learned in class.
- Final group project jointly with a partner company (in the a.y. 2017-2018, this company was Nielsen).
Assessment methods
Continuous assessment | Partial exams | General exam | |
---|---|---|---|
|
x | ||
|
x | ||
|
x | ||
|
x |
ATTENDING STUDENTS
- Team Project: Paper: 45%
- Short-case presentation: 5%
- Final exam: open-ended + multiple choice questions: 50%
- Extra-credit opportunity: Twitter participation: 1 point.
NOT ATTENDING STUDENTS
Exam: open-ended + multiple choice questions (You can consult the Tweepy documentation during the exam).
Teaching materials
ATTENDING STUDENTS
- Slides and articles uploaded to Bboard platform by the instructors
- RUBERA, GROSSETTI, Python for non-Pythonians, Egea (Chapters 1-5 and 7)
- Twitter API documentation available at: https://media.readthedocs.org/pdf/tweepy/v3.2.0/tweepy.pdf
NOT ATTENDING STUDENTS
- TUTEN, SOLOMON, Social Media Marketing, second edition.
- RUBERA, GROSSETTI, Python for non-Pythonians, Egea, (entire book).
- Twitter API documentation available at
Last change 13/09/2019 09:49