Extracting Keywords from Open-Ended Business Survey Questions

Exploring public discourses about emerging technologies through statistical clustering of open-ended survey questions

The primary method by which social scientists describe public opinion about science and technology is to present frequencies from fixed response survey questions and to use multivariate statistical models to predict where different groups stand with regard to perceptions of risk and benefit. Such an approach requires measures of individual preference which can be aligned numerically in an ordin...

Extracting Biological Keywords from Scientific Text

Automated Coding of Open-Ended Survey Responses

Background: Manual coding of open-ended survey responses is time-consuming, expensive, and error-prone. However, this task can be recast as a multi-label text classification problem, to which natural language processing and machine learning techniques can be applied. Aim: The aim of this work is to assess the suitability of various machine learning techniques to the problem of automated coding ...

Extracting Keywords from Digital Document Collections

An indexing tool was built to provide for one of several information seeking tasks. In ac­ cordance with the basic principles of work held by the HUMLE laboratory at SICS, a so­ lution regarding indexing would be a semi-automatic tool. This approach is also relevant as the continuation of the indexing project is conducted in co-operation with the Swedish Parliament, where a staff of professiona...

Extracting Keywords from Multi-party Live Chats

Live chats have become a popular form of communication, connecting people all over the globe. We believe that one of the simplest approaches for providing topic information to users joining a chat is keywords. In this paper, we present a method to automatically extract contextually relevant keywords for multi-party live chats. In our work, we identify keywords that are associated with specific ...