Organizational Unit:

School of Interactive Computing

Permanent Link

https://hdl.handle.net/1853/70783

Parent Organization

Organizational Unit

College of Computing

ArchiveSpace Name Record

https://finding-aids.library.gatech.edu/agents/corporate_entities/1113

Full item page

Publication Search Results

Now showing 1 - 10 of 12

Unsupervised Learning for Lexicon-Based Classification

(Georgia Institute of Technology, 2017) Eisenstein, Jacob

In lexicon-based classification, documents are assigned labels by comparing the number of words that appear from two opposed lexicons, such as positive and negative sentiment. Creating such words lists is often easier than labeling instances, and they can be debugged by non-experts if classification performance is unsatisfactory. However, there is little analysis or justification of this classification heuristic. This paper describes a set of assumptions that can be used to derive a probabilistic justification for lexicon-based classification, as well as an analysis of its expected accuracy. One key assumption behind lexicon-based classification is that all words in each lexicon are equally predictive. This is rarely true in practice, which is why lexicon-based approaches are usually outperformed by supervised classifiers that learn distinct weights on each word from labeled instances. This paper shows that it is possible to learn such weights without labeled data, by leveraging co-occurrence statistics across the lexicons. This offers the best of both worlds: light supervision in the form of lexicons, and data-driven classification with higher accuracy than traditional word-counting heuristics.
Pink Boxes and Chocolate-dipped Broccoli: Bad Game Design Providing Justifications for Reluctant Learners

(Georgia Institute of Technology, 2016-02) DiSalvo, Betsy

The use of games to make boring activities fun is usually a bad idea. The thoughtless use of points and badges as a method of “gamification” is usually a bad idea. Pandering to stereotypes about women by making games pink and on “girly” topics is usually a bad idea. Yet, these design tactics may provide face saving strategies for those who are reluctant to openly engage in learning. In this paper I review tactics such as sugar-coating learning with games, pointsification of educational experiences, and pink boxing games and ask why, if these are such bad design tactics, they sometimes work. In answering these questions the pretense of gaming and fun can be seen as a powerful justification for participation in learning.
Towards a Canine-Human Communication System Based on Head Gestures

(Georgia Institute of Technology, 2015-11) Valentin, Giancarlo ; Alcaidinho, Joelle ; Howard, Ayanna M. ; Jackson, Melody Moore ; Starner, Thad

We explored symbolic canine-human communication for working dogs through the use of canine head gestures. We identified a set of seven criteria for selecting head gestures and identified the first four deserving further experimentation. We devised computationally inexpensive mechanisms to prototype the live system from a motion sensor on the dog’s collar. Each detected gesture is paired with a predetermined message that is voiced to the humans by a smart phone. We examined the system and proposed gestures in two experiments, one indoors and one outdoors. Experiment A examined both gesture detection accuracy and a dog’s ability to perform the gestures using a predetermined routine of cues. Experiment B examined the accuracy of this system on two outdoor working-dog scenarios. The detection mechanism we presented is sufficient to point to improvements into system design and provide valuable insights into which gestures fulfill the seven minimum criteria.
Wearable Alert System for Mobility-Assistance Service Dogs

(Georgia Institute of Technology, 2015-10) Valentin, Giancarlo ; Freil, Larry ; Alcaidinho, Joelle ; Zuerndorfer, Jay ; Mason, Celeste ; Jackson, Melody Moore

We present a study of a wearable alert system for mobility-assistance dogs. Our focus in this study is on assessing sensor and dog activation reliability for the purpose of understanding both system and dog training challenges. We improve on the results from previous work in each of four performance metrics and we present solutions to some practical issues necessary for achieving more reliable and consistent experimental results. We also interviewed active service dog users concerning technical, social and canine considerations, the results of which may inform future studies.
The Challenges of Wearable Computing for Working Dogs

(Georgia Institute of Technology, 2015-09) Valentin, Giancarlo ; Alcaidinho, Joelle ; Jackson, Melody Moore

We present two case studies on creating wearables for dogs and discuss them in terms of challenges of safety, space, weight and comfort, that motivated them. You can use these case studies and our design process as a practical primer for designing wearables for working dogs.
A Dynamic and Dual-Process Theory of Humor

(Georgia Institute of Technology, 2015-05) Li, Boyang

The cognitive mechanism of humor has been studied for centuries, with multiple seemingly incompatible theories proposed. Recent research in emotions suggests human emotions are tightly coupled and closely interact with other types of cognitive processes. This entangled nature contributes to the difficulty of humor research. In this paper, I attempt to provide a single, unified framework of humor, grounded in recent developments on emotion and dual-process cognition. I propose that humor comprehension consists of a four-step dynamic process: surprise, reflection, dismissal and compensation. The proposed theory provides a modern update on existing theories of humor, and is capable of explaining several phenomena that cannot be easily explained by existing theories. I also discuss the implication of the theory on creating computational systems that can create or perceive humor.
From HCI to ACI: User-centered and Participatory design in Canine ACI

(Georgia Institute of Technology, 2014-10-26) Valentin, Giancarlo

As is the case with new scientific disciplines, Animal-Computer Interaction (ACI) has motivated the re-examination of solved and unsolved issues in the philosophy of science. Using canine-human interaction as an example, these challenges are traced back to their roots in existing disciplines. We argue that, as long as research adheres to minimal standards, it should be considered ACI regardless of its stance on these debates.
Assessment of Working Dog Suitability from Quantimetric Data

(Georgia Institute of Technology, 2014-10) Alcaidinho, Joelle ; Valentin, Giancarlo ; Yoder, Nate ; Tai, Stephanie ; Mundell, Paul ; Jackson, Melody Moore

We propose new approaches to assessing the suitability of potential working dogs for a given occupation. The main focus is placed on continuously-recording technology that does not rely on constant human observation. An example is provided in the form of a pilot study relying on activity and human-proximity data collected from dogs both prior to and during advanced training at Canine Companions for Independence. We conclude by noting other technologies that could also be used to achieve this purpose.
An underwater wearable computer for two way human-dolphin communication experimentation

(Georgia Institute of Technology, 2013-09) Kohlsdorf, Daniel ; Gilliland, Scott ; Presti, Peter ; Starner, Thad ; Herzing, Denise

Research in dolphin cognition and communication in the wild is still a challenging task for marine biologists. Most problems arise from the uncontrolled nature of field studies and the challenges of building suitable underwater research equipment. We present a novel underwater wearable computer enabling researchers to engage in an audio-based interaction between humans and dolphins. The design requirements are based on a research protocol developed by a team of marine biologists associated with the Wild Dolphin Project.
Facilitating Interactions for Dogs with Occupations: Wearable Dog - Activated Interfaces

(Georgia Institute of Technology, 2013-09) Jackson, Melody Moore ; Zeagler, Clint ; Valentin, Giancarlo ; Martin, Alex ; Martin, Vincent ; Delawalla, Adil ; Blount, Wendy ; Eiring, Sarah ; Hollis, Ryan ; Kshirsagar, Yash ; Starner, Thad

Working dogs have improved the lives of thousands of people. However, communication between human and canine partners is currently limited. The main goal of the FIDO project is to research fundamental aspects of wearable technologies to support communication between working dogs and their handlers. In this pilot study, the FIDO team investigated on-body interfaces for assistance dogs in the form of wearable technology integrated into assistance dog vests. We created four different sensors that dogs could activate (based on biting, tugging, and nose gestures) and tested them on-body with three assistance-trained dogs. We were able to demonstrate that it is possible to create wearable sensors that dogs can reliably activate on command.