Registration via LPIS
|Thursday||10/14/21||05:00 PM - 07:00 PM||D2.0.030|
|Thursday||10/21/21||05:00 PM - 08:00 PM||D2.0.038|
|Thursday||10/28/21||05:00 PM - 08:00 PM||D2.0.038|
|Thursday||11/04/21||05:00 PM - 08:00 PM||D2.0.038|
|Thursday||11/11/21||05:00 PM - 08:00 PM||D2.0.038|
|Thursday||11/18/21||05:00 PM - 08:00 PM||D2.0.038|
|Thursday||12/09/21||05:00 PM - 08:00 PM||Online-Einheit|
|Thursday||12/16/21||05:00 PM - 08:00 PM||Online-Einheit|
The User Generated Content (UGC) on Social Media platforms produces an impressive quantity of information overload.
This induces the need for summarization, discovery of latent dimensions in the text and the necessity to draw conclusions. The course is a hands-on applicative walk-through Text Mining and Analysis, offering tools and solutions applied to Marketing. Students who enrol in this course will learn from basic to advanced techniques of text manipulation. They would also get an insight into information extraction methods and outcome analysis. The ultimate purpose is to find decision making solutions which are useful for consumers and managers alike.
- Use the R/RStudio environment in order to apply Text Mining and Analysis;
- Autonomously gather text information from various sources;
- Discover latent aspects/dimensions in the text through various techniques:
- Label the discovered aspects/dimensions;
- Do sentiment analysis;
- Summarize text;
- Have an good insight on big volumes of text;
- Understand some popular Machine Learning algorithms applied to Text Analysis;
- Explore Named-Entity Recognition;
- Blend Text Mining and Marketing;
- Draw conclusions based on the results obtained.
The course is based on interactive lectures, class discussions, individual work, and group work. Classroom discussion is encouraged. Attendance and participation in class as well as interactive discussions are key ingredients to successfully learn the material of the course and will be part of your grading. Arriving late or turning in assignments over due time will affect the final grading
• In-class participation, 15%;
• Assignments, 35%;
• Final project, 35%;
• Student presentations, 15%.
The grading scheme is as follows:
< 60% fail (5)
60% to 69,99% sufficient (4)
70% to 79,99% satisfactory (3)
80% to 89,99% good (2)
>= 90% excellent (1)
Some basic R language knowledge. Own laptop computer with R or RStudio installed.
The enrolment in the course is done on a first-come first-served basis. The maximum number of participants is 25.
Author: Free Online Tutorial, R
Author: W. N. Venables, D. M. Smith and the R Core Team
Publisher: R Core Team
Recommendation: Reference literature