Related courses

Recommended prerequisites

Students should have basic knowledge of programming and software design as well as a basic understanding of algorithms and data structures.

Qualification objectives

Students learn about the challenges and methods of text mining and learn how to apply the techniques discussed. They also learn how to apply theoretical approaches to specific, practically relevant issues. For exemplary tasks, students are able to assess existing methodological approaches and suggest further developments or implement them independently. They will be able to argue their case and defend and reflectively evaluate a solution they have found independently.

Contents

In the lecture “Sentiment Analysis”, the already extensive research literature on opinion mining will be reviewed. The approaches range from the text to the word level, the tasks are to recognize subjectivity vs. objectivity, to determine the perspective of authors, to extract their opinion. Data sources can be review sites from the internet, blog posts and comments, messages on Twitter, spoken language, etc.

In the lecture “Social Media Mining”, the development of a system that records, classifies and evaluates messages, news or comments addressed directly or indirectly to companies via social networks is discussed as an example. Text mining and classification methods with a focus on short texts are discussed and the accompanying exercise is deepened in practice.

The lecture “Semantic Technologies” provides an insight into the basics and practical applications of knowledge-based software solutions. It provides a broad overview of the benefits and possibilities of these technologies. Semantic technologies not only enable us to store and retrieve information, but also to evaluate it according to its meaning and function, combine it, link it to new information and thus apply it flexibly and purposefully.

In the module project, students work independently on texts and tasks relating to the module topic under supervision and present their results in an appropriate oral and/or written form. At the beginning of the module project, the individual topics are announced and the form in which the results are to be presented is determined.

Literature

• Allan Ramsay, Tariq Ahmad: Machine Learning for Emotion Analysis in Python, Packt Publishing, 2023.
• Matthew A. Russell, Mikhail Klassen: Mining the Social Web, O'Reilly Media, 2019.
• Archana Patel, Narayan C. Debnath: Data Science with Semantic Technologies, CRC Press, 2023.
• Marc Wintjen: Practical Data Analysis Using Jupyter Notebook, Packt Publishing, 2020.
  
  
  

Proof of performance 

Portfolio: With equal proportions to each of the lectures (with exercises) and in the module project. Students can (depending on what is on offer) submit either two lectures with exercises or one lecture with exercises and a module project. The required individual achievements are as follows:

•  38521: Written examination of 60 minutes or oral examination of 30 minutes. The type of examination will be announced at the beginning of the module.
• 38522: Written examination of 60 minutes or oral examination of 30 minutes. The type of examination will be announced at the beginning of the module.
•  38523: Written examination of 60 minutes or oral examination of 30 minutes. The type of examination will be announced at the beginning of the module.
•  38524: Completion of a project with written documentation, completion time: 8 weeks, 20 pages.

Applicability

The knowledge and skills acquired here supplement the training in the field of software engineering with an aspect of great practical importance. Participation in the courses of this compulsory elective module enables students to undertake a Master's thesis in the field of data science.

Duration and frequency

The module lasts 1 to 2 trimesters and begins each year in HT.

Other remarks

The lectures and the practical course are not all offered every year, but in each year a minimum number of courses are offered to achieve 6 ECTS credits. The specific courses on offer are explained to students at the beginning of each module.