New publication: WiseType: A Tablet Keyboard with Color-Coded Visualization and Various Editing Options for Error Correction

To address the problem of improving text entry accuracy in mobile devices, we present a new tablet keyboard that offers both immediate and delayed feedback on language quality through auto-correction, prediction, and grammar checking. We combine different visual representations for grammar and spelling errors, accepted predictions, auto-corrections, as well as support interactive swiping/tapping features and improved interaction with previous errors, predictions, and auto-corrections. We also added smart error correction features to the system to decrease the overhead of correcting errors and decrease the number of operations. We designed the new input method with an iterative user-centered approach through multiple pilot studies. To determine the effect of our approach, we conducted a lab-based study used a refined methodology and found that WiseType outperforms a standard keyboard in terms of text entry speed and error rate. The study shows that color-coded text background highlighting and underlining of potential mistakes in combination with fast correction methods can improve writing speed and accuracy.

Alharbi, O., Arif A. Sabbir, Stuerzlinger W., Dunlop M. D., & Komninos A. (2019).  WiseType: A Tablet Keyboard with Color-Coded Visualization and Various Editing Options for Error Correction. Graphics Interface - 45th Annual Conference on Computer Graphics, Visualization and Human-Computer Interaction (GI2019). Kingston, Canada, Canadian Human-Computer Communications Society. DOI:10.20380/GI2019.04
Download full text: 

New publication: Pro-social Behaviour in Crowdsourcing Systems: Experiences from a field deployment for beach monitoring

The paper presents experiences from the rapid introduction and deployment of a data crowdsourcing and data sharing system, motivated by an urgent civic need arising due to the appearance of jellyfish in the swimming coastal areas of western Greece during the summer season. The system was tailored for mobile use and although the pressing need for its deployment negated the time for thorough design, a rich set of lessons and findings emerge from its public use by 13,340 users, over a period of 2 months, reporting over 1,800 times on the condition of 189 local beaches, of which 157 were added to the system by the users themselves. This work touches on issues of usability, motivation, data reliability and public utility of mobile participatory systems and demonstrates that effective outcomes for pubic bodies may rise when systems are designed for the immediate benefit of citizens, by openly exposing the collected data. Most importantly, participation in mobile crowdsourced systems where the data is openly shared between participants is found to be strongly driven by altruistic motives and not by financial or ethical awards. Additionally, the altruistic motives behind participation overcome the added difficulty of participating from a purely mobile use context, and safeguard the quality of the contributed data, reducing the need for complex quality monitoring and safeguarding mechanisms. Finally, the paper identifies barriers and opportunities for the opportunistic participation in mobile crowdsourcing systems during leisure time.

Komninos, A. (2019).  Pro-social Behaviour in Crowdsourcing Systems: Experiences from a field deployment for beach monitoring. International Journal of Human-Computer Studies. 124, 93-115., Elsevier. DOI:10.1016/j.ijhcs.2018.12.001
Download full text: 

New publication: Venue Matching in Social Network APIs using Neural Networks

A multitude of social media APIs from popular services such as Facebook, Twitter and Google, allow programmers access to user generated data that is pertinent to physical venues represented within these services. In our paper, we attempt to address the issue of automatically matching venue representations from these diverse APIs, in order to obtain a more complete representation of user cyber-physical interaction with these venues. We present our work comparing a neural network approach against Nearest Point and Longest Common Substring algorithms.

Kalavrouziotis, V., Komninos A., & Garofalakis J. (2018).  Venue Matching in Social Network APIs using Neural Networks. 22nd ACM Panhellenic Conference on Informatics. Athens, Greece, ACM. DOI:https://doi.org/10.1145/3291533.3291558
Download full text: 

Pages