While working on the mobile app for SocialXYZ and after many a few years, I’ve gone ahead and updated the logo image and icon image for SocialXYZ.
The icon, by far is my favorite. I’ve combined the share icon with XYZ. I think it works well.
The logo works too, I think. It’s simple and not as busy as the old one.
I also created a header image for the mobile app pages. It’s simple so as not to distract when users are navigating the app.
My colleagues and I recently published our article, “Real-Time Visualization to Improve Quality in Computer Mediated Communication,” in Web Intelligence. Below is the word cloud of the paper. Below that is the abstract and citation.
Abstract. Within conversational media, how others perceive contributions affects his or her interactions with those contributions. This research explores a novel addition to conversational software, one that provides real-time assessment of quality across user contributions. An analysis of 2,157 online conversations examined attributes of quality, including lexical complexity and prompt-specific vocabulary. These factors helped to inform the redesign of an existing asynchronous online discussion board (AOD). More specifically, a real-time quality analyzer was constructed, which provides users with a visual breakdown of their post in relation to the overall group discussion thread. An experiment across two populations was performed and results found that the system increased overall levels of quality in conversations, while also increasing quality interactions across the system. The results were supplemented with survey data and a social network analysis (SNA), which discovered higher levels of system satisfaction and group cohesion.
Citation
B. Thoms, E. Eryilmaz, N. Dubin, R. Hernandez, S. Colon-Cerezo, “Real-Time Visualization to Improve Quality in Computer Mediated Communication,” Web Intelligence, v18(1), 2020.
Last week I gave a talk up in Sacramento in the School of Business. I was able to tour the campus and meet with the Dean of Business, Bill Cordeiro (previous Dean of Business at CI). Beautiful campus and very fun city. Below is the abstract of the talk.
Abstract: Design Science Research (DSR) focuses on the development and performance of computing artifacts with the explicit intention of improving the functional performance of those artifacts. In this talk, Brian Thoms will introduce his research in social software design. Dr. Thoms will present on the evolution of SocialXYZ, from its origins as a web-based social learning platform to its current state as a cross-platform Android and iOS application. More specifically, Dr. Thoms will discuss how historical data mining, real-time natural language processing and dynamic data analytics affords innovative capabilities for enhancing online conversations. Using recent case studies to illustrate, Dr. Thoms will showcase the art and science of persuasive design, presenting on real-time quality and sentiment analyzing software agents and their input for hybrid recommender systems.
Here is the word cloud for work I co-authored, titled, “Integrating Learning Analytics to Measure Message Quality in Large Online Conversations,” which was presented at the 53rd Hawaii International Conference on System Sciences on January 10, 2020. It received a best paper nomination. This work is a collaborative effort with Asst. Professor Evren Erylimaz.
The paper abstract is as follows:
Abstract: Research on computer-supported collaborative learning often employs content analysis as an approach to investigate message quality in asynchronous online discussions using systematic message-coding schemas. Although this approach helps researchers count the frequencies by which students engage in different socio-cognitive actions, it does not explain how students articulate their ideas in categorized messages. This study investigates the effects of a recommender system on the quality of students’ messages from voluminous discussions. We employ real-time learning analytics to produce a quasi-quality index score for each message. Moreover, we examine the relationship between this score and the phases of a popular message-coding schema. Empirical findings show that a custom CSCL environment extended by a recommender system supports students to explore different viewpoints and modify interpretations with higher quasi-quality index scores than students assigned to the control software. Theoretical and practical implications are also discussed.
Citation
E. Eryilmaz, B. Thoms, KH Lee, M. de Castro, “Integrating Learning Analytics to Measure Message Quality in Large Online Conversations,” Proceedings of Hawaiian International Conference on System Sciences (HICSS 53), January 7-10, 2020, Wailea, HI, USA.
For Fall 2019, I added a new module to the dynamic quality analyzing discussion board and allows users to thumbs-up / thumbs-down and bookmark posts for later. The idea is to integrate the data back into the sites recommender engine, which will showcase relevant content from across the site.
After testing across multiple devices and platforms, I noticed a bug in the recommender panel, which prevents interfacing from iOS devices. Very frustrating! Especially since it works on every other platform including Mac OS. Initially, I wasn’t worried, because how many students would be accessing their coursework through a smartphone, right? Well, it turns out that quite a few will be. A pretest survey found that around 40% of students would be accessing the system through iOS (see below). Therefore, I thought it might be important to correct the bug.
After debugging, I discovered that the bug is common across iOS devices. For some jquery click events, the css needed to be modified to include the attribute cursor: pointer. Very frustrating since android devices work fine. That said, I should have looked the bug up a bit earlier in the debugging process, but all is right as rain.