WKWSCI Sentiment Lexicon v1.1 available for download
A general-purpose English sentiment lexicon called WKWSCI Sentiment Lexicon v1.1 (named after the authors’ school Wee Kim Wee School of Communication & Information) is available for download. The lexicon is based on the 12dicts common American English word lists compiled by Alan Beale from twelve source dictionaries. The lexicon contains 29,729 words tagged with 4 parts-of-speech: adjective, adverb, noun, and verb. The lexicon comprises 3,187 positive words, 7,247 negative words and 19,295 neutral words. WKWSCI Sentiment Lexicon v1.0 was described and compared with five existing lexicons in the paper “Lexicon-Based Sentiment Analysis: Comparative Evaluation of Six Sentiment Lexicons“. Version 1.1 includes some improvements resulting from the reported study....
Article: Comparison of drug information on consumer drug review sites versus authoritative health information websites
Chew, S.H., & Khoo, C.S.G. (2015 early view). Comparison of drug information on consumer drug review sites versus authoritative health information websites. Journal of the American Society for Information Science and Technology.(Available at: http://onlinelibrary.wiley.com/doi/10.1002/asi.23390/abstract) Abstract Huge amounts of health-related information of different types are available on the Web. In addition to authoritative health information sites maintained by government health departments and healthcare institutions, there are many social media sites carrying user-contributed information. This study sought to identify the types of drug information available on consumer-contributed drug review sites compared to authoritative drug information websites—what types of drug information are common and unique, and how they differ in nature, detail and usefulness. Content analysis was carried out on the information available for nine drugs on three authoritative sites (RxList, eMC and PDRhealth), as well as three drug review sites (WebMD, RateADrug and PatientsLikeMe). The types of information found on authoritative...
Article: Issues in information behaviour on social media
Khoo, C.S.G. (2014). Issues in information behaviour on social media. LIBRES, 24(2), 75-96. (Available at: http://libres-ejournal.info/1399/) Abstract Background. Social media present a rich environment to study information behaviour, as much of the user interaction is recorded and stored in publicly accessible repositories and on personal devices. Objectives. This paper surveys the literature of the past nine years on information behaviour related to social media, focusing especially on social networking sites and online discussion forums. It reviews the characteristics of social media users and use, the predominant types of information behaviour, and new types of information found in user-contributed content. Results. Studies have found clear age, gender and national differences, and differences between local citizens and foreigners, in the frequency and purpose of social media use, the choice of social media sites, number of online friends, and types of information posted. Social media users typically share experiential and practical knowledge...
Article: Relevance judgment when browsing a health discussion forum: Content analysis of eye fixations
Pian, W., Khoo, C.S.G., & Chang, Y.K. (2014). Relevance judgment when browsing a health discussion forum: Content analysis of eye fixations. LIBRES, 24(2), 132-147. (Available at: http://libres-ejournal.info/1408/) Abstract Introduction. People are increasingly searching and browsing for health information on social media sites. This is a small study of the relevance criteria used by laypersons when browsing a health discussion forum under three conditions—when seeking information for their own health issue, for a friend’s or relative’s health issue, and with no particular issue in mind. Method. An eye-tracker system was used to identify what text users’ eyes were fixated on when browsing post surrogates and post content on a health discussion forum. Eye-fixations indicated the text segments that the user’s attention was focused on when making relevance judgments. Analysis. Content analysis was performed on the text segments with eye-fixation, to identify the types of information they contain. These types of...
Article: Literature review writing: How information is selected and transformed
Jaidka, K., Khoo, C.S.G., & Na, J.C. (2013). Literature review writing: How information is selected and transformed. Aslib Proceedings, 65(3), 303-325. Abstract Aim. This paper reports a study of researchers’ preferences in selecting information from cited papers to include in a literature review, and the kinds of transformations and editing applied to the selected information. This is a part of a larger project to develop an automatic summarization method that emulates human literature review writing behaviour. Research Questions. How are literature reviews written – where do authors select information from, what types of information do they select and how do they transform it? What is the relationship between styles of literature review (integrative and descriptive) and each of these variables (source sections, types of information and types of transformation)? Method. We analyzed the literature review sections of 20 articles from the Journal of the American Society for Information Science...
Article: Task-based navigation of a taxonomy interface to a digital repository
Khoo, C.S.G., Wang, Z., & Chaudhry, A.S. (2012). Task-based navigation of a taxonomy interface to a digital repository. Information Research, 17(4). (Available at: http://informationr.net/ir/17-4/infres174.html) Abstract Introduction. This is a study of hierarchical navigation; how users browse a taxonomy-based interface to an organizational repository to locate information resources. The study is part of a project to develop a taxonomy for an library and information science department to organize resources and support user browsing in a digital repository. Method. The data collection was carried out using task-based navigation exercises with twenty-two participants. A cognitive framework of hierarchical navigation is proposed, involving the cognitive process of matching context, topic and/or resource type concepts to taxonomy categories. Results. Though users often use the topic concept in making navigation choices, they sometimes make use of context and resource-type concepts. Users infer a variety of relationships between a task concept and a taxonomy category, including...
Article: Sentiment analysis of online news text: A case study of appraisal theory
Khoo, C.S.G., Nourbakhsh, A., & Na, J.C. (2012). Sentiment analysis of online news text: A case study of appraisal theory. Online Information Review, 36(6), 858-878. Abstract Purpose. Sentiment analysis and emotion processing are attracting increasing interest in many fields. Computer and information scientists are developing automated methods for sentiment analysis of online text. Most of the research have focused on identifying sentiment polarity or orientation—whether a document, usually product or movie review, carries a positive or negative sentiment. It is time for researchers to address more sophisticated kinds of sentiment analysis. This paper evaluates a particular linguistic framework called appraisal theory for adoption in manual as well as automatic sentiment analysis of news text. Method. The appraisal theory is applied to the analysis of a sample of political news articles reporting on Iraq and economic policies of George W. Bush and Mahmoud Ahmadinejad to assess its utility and to...
Article: Analysis of the macro-level discourse structure of literature reviews
Khoo, C.S.G., Na, J.-C., and Jaidka, K. (2011). Analysis of the macro-level discourse structure of literature reviews. Online Information Review, 35(2), 255-271. Abstract Purpose . The purpose of this study is to analyze the macro-level discourse structure of literature reviews found in information science journal papers, and to identify different styles of literature review writing. Though there have been several studies of human abstracting, there are hardly any studies of how authors construct literature reviews. This study is carried out in the context of a project to develop a summarization system to generate literature reviews automatically. Method. A coding scheme was developed to annotate the high-level organization of literature reviews, focusing on the types of information. Two sets of annotations were used to check inter-coder reliability. Findings. It was found that literature reviews are written in two distinctive styles, with different discourse structures. Descriptive literature reviews summarize individual...
Article: Design and development of a concept-based multi-document summarization system for research abstracts
Ou, S., Khoo, C.S.G., & Goh, D. (2008). Design and development of a concept-based multi-document summarization system for research abstracts. Journal of Information Science, 34(3), 308-326. Summary: This paper describes a concept-based multi-document summarization system that was developed to summarize sets of dissertation abstracts in sociology that might be retrieved by an information retrieval system or Web search engine in response to a user query. The summarization method developed in this study is a hybrid method comprising four major steps: Macro-level discourse parsing: An automatic discourse parsing method was developed to segment a dissertation abstract into several macro-level sections and identify which sections contain important research information; Information extraction: An information extraction method was developed to extract research concepts and relationships as well as other kinds of information from the micro-level structure (within sentences); Information integration: An information integration method was developed to integrate similar concepts and relationships...
Article: Automatic multi-document summarization of research abstracts: Design and user evaluation
Ou, S., Khoo, C.S.G., & Goh, D. (2007). Automatic multi-document summarization of research abstracts: Design and user evaluation. Journal of the American Society for Information Science & Technology, 58(10), 1419-1435. Summary: This study developed a method for multi-document summarization of sociology dissertation abstracts. We did not use traditional sentence extraction approaches. Instead, a hybrid summarization method involving both extractive and abstractive techniques was used. This method focused on extracting and integrating similarities and differences across different documents to summarize a set of related documents. The identification of similarities and differences was based more on identifying research concepts and relationships expressed in the text, rather than words, phrases or sentences and rhetorical relations used in previous studies. To do that, the macro-level discourse structure (between sentences and segments) peculiar to sociology dissertation abstracts was analyzed to identify which segments of the text contain more important research information. Then the micro-level...