M.A. in Linguistics: Text Mining

The Language Consultancy and Linguistic Documentation specialisation is taught entirely in English. In this specialisation, you will learn to understand language systems, exploring the typological characteristics of languages and how you can classify languages into language families. You will also learn to explain the differences and similarities between languages. With these skills, you can study and describe undescribed languages.

The Text Mining specialisation is also taught entirely in English. In this specialisation, you will look at how to use computer systems to analyse linguistic data as efficiently as possible. The focus here is primarily on large amounts of data, or big data. An essential component is learning how to program, which allows you to control an artificial knowledge system in such a way that it extracts meaningful data from a mountain of linguistic information. To do this, the system must understand how that language works. As a programmer, therefore, you will also learn about language systems so you can teach this to the computer. In this specialisation, you will, therefore, make the connection between linguistics and artificial intelligence.

The start date of this programme is September 1st.

Find out what the different possibilities are within the master's programme.

Language Consultancy and Linguistic Documentation

Study linguistic diversity & language in its cultural context

Within the Master’s programme in Linguistics, the Language Consultancy and Linguistic Documentation specialisation focuses on the interaction between theory and data in the research traditions of anthropological, typological and descriptive linguistics. The programme’s emphasis on practical fieldwork, cultural pragmatics and anthropological perspectives makes it unique in the Netherlands. When you graduate, you will have the knowledge, skills and expertise to function as a linguistic consultant or linguistic researcher in many settings, particularly in translation, cross-cultural communication and language documentation.

In this specialisation, you will focus on developing:

• knowledge of current developments in the fields of typological, descriptive and anthropological linguistics
• the ability to reflect critically on scholarly publications in these fields
• the skills to carry out linguistic research in fieldwork and cross-cultural linguistic consultancy settings
• the ability to communicate the results of your research clearly and systematically to fellow linguists and to the general public
• the ability to write a reference grammar of an under-documented language in accordance with the international standards of descriptive and documentary linguistics

In the first semester, you will take three specialist courses:

• Articulatory Phonetics & the Typology of Sounds
• Linguistic Research
• Describing Morphosyntax

In the second semester, you will take two more specialist courses:

• Anthropological Linguistics
• Field Methods & Linguistic Analysis

You will also choose elective courses and/or tutorials in both semesters. In addition, you will write your Master’s thesis during the second semester under the guidance of a member of our academic staff.

Text Mining

Connecting the humanities, social sciences & computer science

In order to get meaningful information from very large repositories of text, you need to know what you are looking for and how to find it. The Text Mining specialisation of the Master’s programme in Linguistics teaches you how to mine text by applying Artificial Intelligence techniques.

What is text mining?

There is more digital information available than ever before. But how can we use this availability of information to improve society? By applying Artificial Intelligence techniques, you can teach a computer how to search through enormous amounts of textual data to find information or make connections that have previously alluded scientists and decision-makers. For example:

• countless medical reports and scientific papers on specific symptoms contain information that could lead to better treatments and cures for diseases
• an abundance of documents on economic policies and their effects could lead to improved decision making and stronger economies
• the opinions of millions of people on all kinds of topics are available on social media, which could help us understand issues like how propaganda and misinformation is spread, how language is evolving and even how people deal with anxiety
• historical archives, libraries with centuries of books are now available digitally, and exploring them through new techniques could give us a deeper understanding of history and religion

Useful for all fields of knowledge

Although text mining is grounded in linguistics, computer science and Artificial Intelligence, it is extremely relevant for almost all fields of knowledge. That is why the programme is open to graduates in nearly every academic discipline. As a graduate with expertise in your field of knowledge, you know what kind of information to look for within your discipline. With the Master’s specialisation in Text Mining, you will become a pioneer in the analysis of textual big data using Artificial Intelligence techniques. You bring your disciplinary expertise; we teach you the tools and techniques to advance your discipline by mining big data.

Programme structure

In the first period, you will learn the basics of linguistics and programming in Python for Text Analysis.

The second period brings you more specialised knowledge and skills as you learn how to look at language as data and how to use methods and tools for the processing of language in the course NLP Foundations.

In periods three and four, you will really dive into text mining. In Applied Text Mining, you will gain hands-on experience in building a ‘reading machine’. In Text Mining in Domains, you will apply your newly acquired knowledge in your professional domain. At the same time, you will follow a course in Machine Learning, which focuses on working with language.

Master thesis

You will write your Master’s thesis in the last two periods, probably based on an internship in the language industry. Every year we organise a meet and greet where institutes and companies visit us to meet our students and talk about the possibilities for internships.