- 105 views
- 85 downloads
Analysis of an Extracted Discipline-Specific Computer Science Vocabulary List
- Author(s) / Creator(s)
A strong vocabulary allows for more understanding. Vocabulary can be categorized into 3 tiers.
Tier 1 contains commonplace and basic vocabulary. Tier 2 words are used by mature speakers
across a variety of subject matters. Tier 3 contains low-frequency words that are used in specific
disciplines. To gain conceptual knowledge in academic domains, a strong foundation of Tier 3
vocabulary is essential. Many disciplines do not have a vocabulary list in place, making the
learning process more difficult. Computer science is one such discipline, which is why this
project aims to create a method for automatically creating a computer science vocabulary list.
Starting with a premade computer-science corpus, a computer-science vocabulary list is extracted
using computational linguistics techniques. This includes removing unrelated words from the list
by extracting text from a compilation of non-computer science resources and using the extracted
text to remove any similar words from the original vocabulary list. The resulting list could help
enhance student learning in computer science and this process could be duplicated for creating
another discipline-specific vocabulary list.
- Date created
- Subjects / Keywords
- Type of Item
- Conference/Workshop Poster