Overview and details of the sessions of this conference. Please select a date or room to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Predicting the influence of microblog entries regarding public health emergencies
Lu An1, Xingyue Yi1, Chuanming Yu2, Gang Li1
1Wuhan University, China, People's Republic of; 2Zhongnan University of Economics and Law, People’s Republic of China
Predicting the influence of microblog entries regarding public health emergencies can help management departments improve the prospectiveness of decision making. In this study, we measure the influence of microblog entries regarding public health emergencies from their forwarding, comment and favorite counts. A microblog influence prediction model, which is comprised of user, time and content features, is proposed by using the random forest method and the BM25 Latent Dirichlet Allocation model (LDA-BM25). Microblog entries on the Ebola outbreak are selected as test data. Results reveal that the proposed model can accurately predict the influence of microblog entries regarding public health emergencies with the accuracy rate reaching 88.8%. Individual features, which play a role in the influence of microblog entries, and their influence inclination are also analyzed. The findings of the study can help management departments of public health emergencies predict the upcoming salient issues, and take appropriate measures in advance.
Extracting customer concerns from online reviews of series products for competitor analysis
Sixing Yan1, Jian Jin1, Ping Ji2, Zihao Geng3
1Department of Information Management, Beijing Normal University, People's Republic of China; 2Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University; 3School of Industrial & Systems Engineering, Georgia Institute of Technology, GA
Online reviews provide valuable information for product designers, and the integration of online concerns into new product design has been investigated by different researchers. However, few researchers exploit how to apply online concerns in the competitor analysis about the merits and drawbacks of series products. Accordingly, in this research, a framework is presented to sample representative sentences from online reviews, aiming to highlight similar customer concerns of series products. First, opinionated sentences of specific features are identified. Then, opinionated sentences in the same series products are clustered to extract similar customer concerns. Finally, an optimization problem is formulated for sampling a few representative sentences. With real data from Amazon.com, categories of experiments were conducted to evaluate the effectiveness of the proposed approach. This study explores the possibility about integrating big consumer data into competitor analysis in the market driven product design, which is essentially critical in fierce market competition.
Towards an Integrated Clickstream Data Analysis Framework for Understanding Web Users' Information Behavior
Yu Chi1, Tingting Jiang2, Daqing He1, Rui Meng1
1School of Information Sciences, University of Pittsburgh; 2School of Information Management, Wuhan University
Clickstream data offers an unobtrusive data source for understanding web users’ information behavior beyond searching. However, it remains underutilized due to the lack of structured analysis procedures. This paper provides an integrated framework for information scientists to employ in their exploitation of clickstream data, which could contribute to more comprehensive research on users’information behavior. Our proposed framework consists of two major components, i.e., data preparation and data investigation. Data preparation is the process of collecting, cleaning, parsing, and coding data, whereas data investigation includes examining data at three different granularity levels, namely, footprint, movement, and pathway. To clearly present our data analysis process with the analysis framework, we draw examples from an empirical analysis of clickstream data of OPAC users’ behavior. Overall, this integrated analysis framework is designed to be independent of any specific research settings so that it can be easily adopted by future researchers for their own clickstream datasets and research questions.