A Picture is Worth a Thousand Words

Kim, Joon-Gyum; Wu, Chia-Wei; Chiang, Alvin; Ko, JeongGil; Lee, Sung-Ju

doi:10.1145/2873587.2873602

Cited by 6 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the idea and challenges of image recommendation based on the currently typed word in mobile chat has been recently reported [28], contrary to our work, it does not suggest technical details in image search phrase extraction, word type selection, or dependency parsing that are required in realizing real-time image suggestions in mobile chat. Moreover, it lacks user studies that investigate how image recommendation affects mobile user chat behavior.…”

Section: Visual Support For Mobile Chatscontrasting

confidence: 82%

“…MilliCat recommends images in real-time to alleviate users from inconveniences when using images within a mobile chat. Users also reported preferences in autonomously being suggested images from the Internet, based on the chat input text [28]. MilliCat takes in user's input text to the mobile chat application, analyzes the text to identify suitable words for image suggestion, fetches proper images from the Internet, and presents options that the users can choose from to embed image in their chats.…”

Section: Millicat Designmentioning

confidence: 99%

“…We designed MilliCat to divide the functionalities between the mobile and the server so that the load on mobile devices is reduced. MilliCat leverages server capabilities when running NLP algorithms [28]. Below we detail our technical solutions for realizing real-time image suggestions in mobile chat.…”

Section: Millicat Designmentioning

confidence: 99%

“…Personal images [11,29] are useful in sharing deep personal and social context. We argue that public images on the Internet could be useful for sharing information and emphasizing opinion on mobile chats [28]. Moreover, current mobile chat apps require users to spend tedious steps to include public images in a chat; the user typically goes through other applications to find, store, and retrieve a desired image, then uses the original mobile chat app's features to include the image in the chat room.…”

Section: Introductionmentioning

confidence: 99%

“…We believe that having autonomous real-time image suggestions can alleviate such user inconveniences when using images within a mobile chat. Moreover, it was reported in a survey [28] that 81.57% of survey participants prefer to be autonomously suggested images from the Internet, based on the chat application input text. To validate such hypothesis, we present the design and implementation of MilliCat, a system that autonomously and selectively suggests images with respect to the user's input text in a mobile chat application.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Messaging Beyond Texts with Real-time Image Suggestions

Kim

Gong

Han

et al. 2020

22nd International Conference on Human-Computer Interaction With Mobile Devices and Services

Self Cite

View full text Add to dashboard Cite

While people primarily communicate with text in mobile chat applications, they are increasingly using visual elements such as images, emojis, and memes. Using such visual elements could help users communicate clearly and make chatting experience enjoyable. However, finding and inserting contextually appropriate images during the chat can be both tedious and distracting. We introduce Milli-Cat, a real-time image suggestion system that recommends images that match the chat content within a mobile chat application (i.e., autocomplete with images). MilliCat combines natural language processing (e.g., keyword extraction, dependency parsing) and mobile computing (e.g., resource and energy-efficiency) techniques to autonomously make image suggestions when users might want to use images. Through multiple user studies, we investigated the effectiveness of our design choices, the frequency and motivation of image usage by the participants, and the impact of MilliCat on mobile chat experiences. Our results indicate that MilliCat's realtime image suggestion enables users to quickly and conveniently select and display images on mobile chat by significantly reducing the latency in the image selection process (3.19× improvement) and consequently more frequent image usage (1.8×) than existing solutions. Our study participants reported that they used images more often with MilliCat as the images helped them convey information more effectively, emphasize their opinion, express emotions, and have fun chatting experience. CCS CONCEPTS • Human-centered computing → Interactive systems and tools; Empirical studies in interaction design; Ubiquitous and mobile computing systems and tools.

show abstract

Section: Visual Support For Mobile Chatscontrasting

confidence: 82%

Section: Millicat Designmentioning

confidence: 99%

Section: Millicat Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Messaging Beyond Texts with Real-time Image Suggestions

Kim

Gong

Han

et al. 2020

22nd International Conference on Human-Computer Interaction With Mobile Devices and Services

Self Cite

View full text Add to dashboard Cite

show abstract

Auto Response Generation in Online Medical Chat Services

Jahanshahi

Kazmi

Çevik

2022

J Healthc Inform Res

View full text Add to dashboard Cite

Telehealth helps to facilitate access to medical professionals by enabling remote medical services for the patients. These services have become gradually popular over the years with the advent of necessary technological infrastructure. The benefits of telehealth have been even more apparent since the beginning of the COVID-19 crisis, as people have become less inclined to visit doctors in person during the pandemic. In this paper, we focus on facilitating chat sessions between a doctor and a patient. We note that the quality and efficiency of the chat experience can be critical as the demand for telehealth services increases. Accordingly, we develop a smart auto-response generation mechanism for medical conversations that helps doctors respond to consultation requests efficiently, particularly during busy sessions. We explore over 900,000 anonymous, historical online messages between doctors and patients collected over 9 months. We implement clustering algorithms to identify the most frequent responses by doctors and manually label the data accordingly. We then train machine learning algorithms using this preprocessed data to generate the responses. The considered algorithm has two steps: a filtering (i.e., triggering) model to filter out infeasible patient messages and a response generator to suggest the top-3 doctor responses for the ones that successfully pass the triggering phase. Among the models utilized, BERT provides an accuracy of 85.41% for precision@3 and shows robustness to its parameters. KeywordsNatural language processing • AI and healthcare • Smart chat reply • Medical services • Deep learning * Hadi Jahanshahi

show abstract

Demo

Kim

Lee

2016

Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services Companion

View full text Add to dashboard Cite

A Picture is Worth a Thousand Words

Cited by 6 publications

References 3 publications

Messaging Beyond Texts with Real-time Image Suggestions

Messaging Beyond Texts with Real-time Image Suggestions

Auto Response Generation in Online Medical Chat Services

Demo

Contact Info

Product

Resources

About