Word Space Creator: A Visual Tool for Semantic Space Visualization

Semantic spaces are used as a representation of language, capturing the meaning between linguistic units. These spaces are often built in large corpora requiring advanced equipment, specialized computational skills, and considerable effort. This project note will introduce and demonstrate the use of an accessible Shiny graphical interface allowing users to create semantic space models easily. Shiny is an R package in which one can program interactive web applications in R for others to interact with data or analyses. The advantage to Shiny applications is that naïve users can explore data without understanding the programming, and open sharing of code with the application can aid in learning the programming for one’s own use in their research. Within the application, users will be able to load popular semantic spaces or their own corpus for semantic space creation utilizing their preferred modeling technique, including LSA and TOPICS. A variety of user-friendly graphical tools, such as n-nearest neighbors or topic weighted graph, will further aid data visualization of the semantic network. Additionally, the application provides the calculation of cosine or simple co-occurrence, among other popular-relatedness values. This tool is intended for researchers who may not be programming-savvy, or as a teaching extension for psycholinguistics courses.

语义空间被用作语言的表现形式，捕捉语言单位之间的意义。此类空间通常在大规模语料库中构建，需要高级设备、专业的计算技能以及相当大的努力。本项研究笔记将介绍并展示一款易于使用的Shiny图形界面，该界面允许用户轻松创建语义空间模型。Shiny是一个R语言包，用户可以使用它编程交互式网络应用，以便他人可以与数据或分析进行交互。Shiny应用的优势在于，即使是非专业用户也可以在不理解编程的情况下探索数据，并且与应用程序一起共享代码可以有助于学习编程，以便在自己的研究中使用。在应用中，用户将能够加载流行的语义空间或自己的语料库，以使用他们偏好的建模技术创建语义空间，包括LSA和TOPICS。一系列用户友好的图形工具，如n-最近邻或主题加权图，将进一步协助语义网络的可视化。此外，该应用还提供计算余弦或简单共现等流行相关性值的功能。该工具旨在为可能不擅长编程的研究人员设计，也可作为心理语言学课程的教辅工具。