Ruixuan Sun

Ruixuan Sun

Auto-generated profile, based on publicly available information

Ruixuan Sun

Grouplens Research, University of Minnesota - Twin Cities, Minneapolis, Minnesota, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 April 2023
Verified
Conference Paper
Open access
QJQiao Jin
Qiao Jin
YLYu Liu
Yu Liu
RSRuixuan Sun
Ruixuan Sun
CCChen Chen
Chen Chen
PZPuqi Zhou
Puqi Zhou
SYSvetlana Yarosh
Svetlana Yarosh
Virtual Reality (VR) has a noteworthy educational potential by providing immersive and collaborative environments. As an alternative but cost-effective way of delivering realistic environments in VR, using 360-degree videos in immersive VR (VR videos) received more attention. Although many studies reported positive learning experiences with VR videos, little is known about how collaborative learning performs on VR video viewing systems. In this study, we implemented two collaborative VR video viewing modes based on the way of group video control, synchronized or shared (Sync mode) and non-synchronized or individual (Non-sync mode) video control, against a conventional VR video viewing setting (Basic mode). We conducted a within-subject study (N = 54) in a lab-simulated remote learning environment. Our results show that collaborative VR video modes (Sync and Non-sync mode) improve users’ learning experiences and collaboration quality, especially with shared video control. Our findings provide directions for designing and employing collaborative VR video tools in online learning environments.

5 October 2023 in International Journal of Human–Computer Interaction
Verified
Journal Article
Closed access
RSRuixuan Sun
Ruixuan Sun
AAAvinash Akella
Avinash Akella
RKRuoyan Kong
Ruoyan Kong
MZMoyan Zhou
Moyan Zhou
JKJoseph A. Konstan
Joseph A. Konstan

20 July 2022 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
FLFan Li
Fan Li
HQHong Qu
Hong Qu
MFMingsheng Fu
Mingsheng Fu
LZLiyan Zhang
Liyan Zhang
FZFan Zhang
Fan Zhang
HZHaixian Zhang
Haixian Zhang
Reranking is a critical task used to refine the initial collaborative filtering (CF) recommendation by incorporating information from different viewpoints, such as the extra item side-information and user profile. In this article, a neural reranking-based CF (NRCF) model is proposed to leverage composite viewpoints from the basic CF model and user preference. More precisely, the predictive implicit user preference is first constructed from the initial top- $k$ items. The implicit user preference is then aggregated with the explicit user embedding to enrich the user intent representation. Moreover, the traditional listwise loss functions for reranking optimization are suboptimal, due to the fact that they neglect the relative ranking information (ReinRank) between the unobserved and positive items. To address this issue, a novel listwise loss function that leverages relative ranking information, referred to as ReinRank, is proposed for reranking optimization. ReinRank assigns different values to the unobserved items, according to their relative ranking distances between the positive items. Extensive experiments are performed on three public benchmarks and different CF models, in order to demonstrate the effectiveness of NRCF and ReinRank.

30 May 2023
Verified
Conference Paper
Open access
RKRuoyan Kong
Ruoyan Kong
RSRuixuan Sun
Ruixuan Sun
CZCharles Chuankai Zhang
Charles Chuankai Zhang
CCChen Chen
Chen Chen
SPSneha Patri
Sneha Patri
JKJoseph A. Konstan
Joseph A. Konstan
A single digital newsletter usually contains many messages (regions). Users’ reading time spent on, and read level (skip/skim/read-in-detail) of each message is important for platforms to understand their users’ interests, personalize their contents, and make recommendations. Based on accurate but expensive-to-collect eyetracker-recorded data, we built models that predict per-region reading time based on easy-to-collect Javascript browser tracking data. With eye-tracking, we collected 200k ground-truth datapoints on participants reading news on browsers. Then we trained machine learning and deep learning models to predict message-level reading time based on user interactions like mouse position, scrolling, and clicking. We reached 27% percentage error in reading time estimation with a two-tower neural network based on user interactions only, against the eye-tracking ground truth data, while the heuristic baselines have around 46% percentage error. We also discovered the benefits of replacing per-session models with per-timestamp models, and adding user pattern features. We concluded with suggestions on developing message-level reading estimation techniques based on available data.

16 June 2023
Verified
Conference Paper
Open access
RSRuixuan Sun
Ruixuan Sun
RKRuoyan Kong
Ruoyan Kong
QJQiao Jin
Qiao Jin
JKJoseph Konstan
Joseph Konstan
In this study, we partition users by rating disposition - looking first at their percentage of negative ratings, and then at the general use of the rating scale. We hypothesize that users with different rating dispositions may use the recommender system differently and therefore the agreement with their past ratings may be less predictive of the future agreement. We use data from a large movie rating website to explore whether users should be grouped by disposition, focusing on identifying their various rating distributions that may hurt recommender effectiveness. We find that such partitioning not only improves computational efficiency but also improves top-k performance and predictive accuracy. Though such effects are largest for the user-based KNN CF, smaller for item-based KNN CF, and smallest for latent factor algorithms such as SVD.

8 October 2024
Verified
Conference Paper
Open access
RSRuixuan Sun
Ruixuan Sun
This is a dissertation plan built around human-centered empirical experiments evaluating recommender systems (RecSys). We see this as an important research theme since many AI-based RecSys algorithmic studies lack real human assessment. Therefore, we do not know how they work in the wild that only human experiments can tell us. We split this extended abstract into two parts – 1) A series of individual studies focusing on open questions about different human values or recommendation algorithms. Our completed works include user control over content diversity, user appreciation on DL-RecSys algorithms, and human-LLMRec interaction study. We also propose three future works to understand news recommendation depolarization, personalized news podcast, and interactive user representation; 2) An experimentation infrastructure named POPROX. As a personalized news recommendation platform, it aims to support the longitudinal study needs from the general AI and RecSys research community.