Professor Ozgur Turetken (Ph.D., Oklahoma State University, MBA, BS METU, Ankara, Turkey) joined TRSITM in 2006. Prior to that, he served on the faculty of Temple University Fox School of Business and Management for 6 years. Dr. Turetken's scholarly interests are mainly in applied (text) analytics especially in the context of individual decision making. His research on the organization and presentation of information as they relate to decision outcomes has been published in international journals and conferences, and has been funded by NSERC and SSHRC among other agencies. Ozgur is also a recipient of Ryerson SRC award in 2010. He is active in various research communities as an editor, special interest group officer, and track chair. He has developed and taught many undergraduate and graduate courses, mostly in evidence based management and supervised several theses. Ozgur also served in many committees at the departmental, faculty, and university levels at Ryerson. His service contributions have been recognized by the 2010 TRSM Service Award.
Areas of Expertise (6)
Scholarly Research and Creative Activity Award (professional)
Ryerson University, Ted Rogers School of Management
Service Award (professional)
Ryerson University, Ted Rogers School of Management
Oklahoma State University: PhD, Business Administration-Management Science and Information Systems
Middle East Technical University: MBA, Management
Middle East Technical University: BSc, Electrical Engineering
Selected Articles (5)
Michal Szczech & Ozgur Turetken
Google Trends, the service that illustrates the trends in Google search activity, has recently received attention form analytics researchers for the prediction of economic trends and consumer behavior. Previous studies used Google Trends to estimate consumption and sales for a particular business, or provide general trends for an economic sector or industry. This study reported here differs from these attempts as it aims to estimate the performance of a single player in an industry by not only trends related to that player, but also those of its competitors. Further, these trends have been modified by Twitter based sentiment scores. It is demonstrated that the incorporation of competitive factors results in better estimates by as much as 5% while the addition of a Twitter sentiment score is not beneficial. The Twitter related findings could be because the tweet volumes in the particular industry that was examined are low and volatile.
Haiqing Li, Samir Chatterjee, & Ozgur Turetken
With advances in information and communication technologies (ICT), organizations of various forms now deploy an increasing number of ICT-enabled persuasive systems in several domains. Traditional computer-mediated communication (CMC) theories mainly focus on the effectiveness of media in the synchronous/asynchronous spectrum for effectively matching medium with communication task. The contemporary communication environment is rich with asynchronous channels such as email, Web, and text messaging, which makes it important to go beyond synchronicity and determine the nuances among various asynchronous channels. No rigorous research has compared the effectiveness of these channels in the persuasive systems domain where organizations use technology to persuade users to modify their behavior in a direction that they mutually agree to be desirable. In this paper, we study the effectiveness of CMC and the strategy used to frame the persuasive message. We explore persuasive strategies of praising, reminding, suggesting, and rewarding for health behavior and promotion. We model user experience as a mediator between channel strategy combinations and persuasive effectiveness. Through controlled user studies, we compared sixteen combinations of communication channel and persuasive strategy with or without emoticons. We found that channel/strategy combinations affect persuasive effectiveness (mediated by user experience) in varying degrees. Our findings contribute to the body of CMC and persuasive system knowledge and have practical implications for online advertising, health promotion, and persuasive technology design.
Parisa Lak & Ozgur Turetken
User-generated online content serves as a source of product- and service-related information that reduces the uncertainty in consumer decision making, yet the abundance of such content makes it prohibitively costly to use all relevant information. Dealing with this (big data) problem requires a consumer to decide what subset of information to focus on. Peer-generated star ratings are excellent tools for one to decide what subset of information to focus on as they indicate a review’s “tone”. However, star ratings are not available for all user-generated content and not detailed enough in other cases. Sentiment analysis, a text-analytic technique that automatically detects the polarity of text, provides sentiment scores that are comparable to, and potentially more refined than, star ratings. Despite its popularity as an active topic in analytics research, sentiment analysis outcomes have not been evaluated through rigorous user studies. We fill that gap by investigating the impact of sentiment scores on purchase decisions through a controlled experiment using 100 participants. The results suggest that, consistent with the effort-accuracy trade off and effort-minimization concepts, sentiment scores on review documents improve the efficiency (speed) of purchase decisions without significantly affecting decision effectiveness (confidence).
Ozgur Turetken & Sameh Al-Natour
Research has consistently shown that online word-of-mouth (WOM) plays an important role in shaping customer attitudes and behaviors. Yet, despite their documented utility, explicit user scores, such as star ratings have limitations in certain contexts. Automatic sentiment analysis (SA), an analytics technique that assesses the “tone” of text, has been proposed as a way to deal with these shortcomings. While extant research on SA has focused on issues surrounding the design of algorithms and output accuracy, this research-in-progress examines the behavioral and interface design issues in regards to SA scores as perceived by their intended users. Specifically, in an online context, we experimentally investigate the role of product (product category) and review characteristics (review extremity) in influencing the perceived usefulness of SA scores. Further, we investigate whether variations in how the SA scores are presented to the user, and the nature of the scores themselves further affect user perceptions.
Barbara Wixom, Thilini Ariyachandra, David Douglas, Michael Goul, Babita Gupta, Lakshmi Iyer, Uday Kulkarni, John G Mooney, Gloria Phillips-Wren, & Ozgur Turetken
In December 2012, the AIS Special Interest Group on Decision Support, Knowledge and Data Management Systems (SIGDSS) and the Teradata University Network (TUN) cosponsored the Business Intelligence Congress 3 and conducted surveys to assess academia's response to the growing market need for students with Business Intelligence (BI) and Business Analytics (BA) skill sets. This panel report describes the key findings and best practices that were identified, with an emphasis on what has changed since the BI Congress efforts in 2009 and 2010. The article also serves as a “call to action” for universities regarding the need to respond to emerging market needs in BI/BA, including “Big Data.” The IS field continues to be well positioned to be the leader in creating the next generation BI/BA workforce. To do so, we believe that IS leaders need to continuously refine BI/BA