Wenxuan Song

Wenxuan Song

Auto-generated profile, based on publicly available information

Wenxuan Song

School of Information Sciences, University of Illinois Urbana-Champaign, Champaign, USA

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
21 January 2026 in arXiv
Verified
Preprint
Open access
PDF file
SZShanshan Zhu
Shanshan Zhu
WSWenxuan Song
Wenxuan Song
JSJiayue Melissa Shi
Jiayue Melissa Shi
DYDong Whi Yoo
Dong Whi Yoo
KBKarthik S. Bhat
Karthik S. Bhat
KSKoustuv Saha
Koustuv Saha
Most personal wellbeing apps present summative dashboards of health and physical activity metrics, yet many users struggle to translate this information into meaningful understanding. These apps commonly support engagement through goals, reminders, and structured targets, which can reinforce comparison, judgment, and performance anxiety. To explore a complementary approach that prioritizes self-reflection, we design KRIYA, an AI wellbeing companion that supports co-interpretive engagement with personal wellbeing data. KRIYA aims to collaborate with users to explore questions, explanations, and future scenarios through features such as Comfort Zone, Detective Mode, and What-If Planning. We conducted semi-structured interviews with 18 college students interacting with a KRIYA prototype using hypothetical data. Our findings show that through KRIYA interaction, users framed engaging with wellbeing data as interpretation rather than performance, experienced reflection as supportive or pressuring depending on emotional framing, and developed trust through transparency. We discuss design implications for AI companions that support curiosity, self-compassion, and reflective sensemaking of personal health data.


13 April 2026
Verified
Conference Paper
Open access
KBKarthik S Bhat
Karthik S Bhat
JSJiayue Melissa Shi
Jiayue Melissa Shi
WSWenxuan Song
Wenxuan Song
DYDong Whi Yoo
Dong Whi Yoo
KSKoustuv Saha
Koustuv Saha
Screen use pervades daily life, shaping work, leisure, and social connections while raising concerns for digital wellbeing. Yet, reducing screen time alone risks oversimplifying technology’s role and neglecting its potential for meaningful engagement. We posit self-awareness—reflecting on one’s digital behavior—as a critical pathway to digital wellbeing. We developed WellScreen, a lightweight probe that scaffolds daily reflection by asking people to estimate and report smartphone use. In a two-week deployment with college students ( \(\mathtt {N}\) =25) focused on generating formative insights, we examined how discrepancies between estimated and actual usage shaped digital awareness and wellbeing. Participants often underestimated productivity and social media while overestimating entertainment app use. They showed a 10% improvement in positive affect, rating WellScreen as moderately useful. Interviews revealed that structured reflection supported recognition of patterns, adjustment of expectations, and more intentional engagement with technology. Our findings highlight the promise of lightweight reflective interventions for supporting self-awareness and intentional digital engagement, offering implications for designing digital wellbeing tools.

30 October 2026 in JMIR Preprints
Verified
Preprint
Open access
SZShanshan Zhu
Shanshan Zhu
WSWenxuan Song
Wenxuan Song
JSJiayue Melissa Shi
Jiayue Melissa Shi
DYDong Whi Yoo
Dong Whi Yoo
KBKarthik S. Bhat
Karthik S. Bhat
KSKoustuv Saha
Koustuv Saha
BACKGROUND Personal wellbeing applications commonly summarize steps, sleep, and activity through dashboards, goals, and reminders. These features support progress tracking but offer limited support for interpreting why personal data vary across everyday contexts. OBJECTIVE This study examined how college students perceived the clarity, anticipated usefulness, and appropriateness of co-interpretive interaction strategies in KRIYA, an envisioned AI-supported interface for personal wellbeing reflection. METHODS We conducted semi-structured remote interviews with 20 college students. Participants discussed their existing health-tracking practices and completed a guided walkthrough of a high-fidelity prototype using hypothetical wellbeing scenarios and pre-authored conversational responses. The prototype instantiated range-based framing, context-aware discrepancy interpretation, and speculative low-stakes planning. We analyzed interview transcripts using reflexive thematic analysis and descriptively summarized post-walkthrough System Usability Scale (SUS) and Intervention Appropriateness Measure (IAM) scores. RESULTS Participants perceived range-based framing as a more flexible way to consider daily variation, valued context-linked explanations as starting points for interpretation, and viewed small, revisable actions as manageable. They expected envisioned AI interpretations to remain legible, bounded, and open to correction. Perceived value diminished when ranges felt arbitrary, explanations were generic, or numerical outputs lacked clear provenance. The median SUS score was 76.25 (SD 11.18), and the median IAM score was 14.0 (SD 2.78). These scores describe perceptions of the facilitated walkthrough and proposed interaction concept. CONCLUSIONS The findings identify design considerations for AI-supported personal wellbeing interfaces: contextual explanations should remain tentative and revisable, ranges should be plausible and adjustable, and speculative planning should communicate uncertainty and predictive limits. The study provides formative qualitative evidence about user perceptions; it does not establish behavior change, clinical benefit, or forecasting accuracy.

15 June 2026 in medRxiv
Verified
Preprint
Open access
LJLan Jiang
Lan Jiang
XYXiangji Ying
Xiangji Ying
ABAndrew Brown
Andrew Brown
MLMengfei Lan
Mengfei Lan
WSWenxuan Song
Wenxuan Song
HKHalil Kilicoglu
Halil Kilicoglu
Randomized controlled trials (RCTs) play a central role in assessing the benefits and harms of interventions. Incomplete reporting in RCT publications can compromise the verifiability and usefulness of RCTs. SPIRIT and CONSORT reporting guidelines aim to improve the completeness of RCT protocols and results publications, respectively. However, many RCTs are not reported completely. Checking manuscripts automatically could help authors improve the completeness of reports prior to publication. We previously annotated SPIRIT-CONSORT-TM, a corpus of 200 articles (comprising 100 protocol-results publication pairs) using 83 checklist items drawn from SPIRIT 2013 and CONSORT 2010. We also trained machine learning models to automatically assess reporting at the item level. Each checklist item can include multiple constituent elements (i.e., specific details required for that item), and an item might be considered fully reported when all of its elements are present. However, prior work does not explicitly capture or evaluate reporting at the element level. To address this gap, we extended SPIRIT-CONSORT-TM by incorporating element-level annotations and using them to assess reporting completeness (SPIRIT-CONSORT-ELM). We formulated element-level assessment as a machine reading comprehension task, operationalized through 119 questions, where each question targets a specific reporting element within a checklist item. Using the 200 articles included in SPIRIT-CONSORT-TM, two annotators independently answered 119 questions for 50 articles (25 protocol-results pairs) and resolved any discrepancies through discussion; the remaining 150 articles (75 protocol-results pairs) were assessed by a single annotator. We then developed an automated pipeline for element-level assessment using SPIRIT-CONSORT-ELM. The pipeline first applies a PubMedBERT-based model to identify sentences containing item-level reporting information, then it uses a generative large language model (LLM; GPT-5) with chain-of-thought reasoning to answer element-level questions based on the retrieved evidence. Agreement between the two annotators was high (Gwet’s AC1: 0.782) and our pipeline achieved high accuracy in identifying element-level reporting evidence (F1: 0.822, Gwet’s AC1: 0.796). Ablation studies indicate that chain-of-thought reasoning and the inclusion of illustrative in-context examples modestly improve LLM performance on the machine reading comprehension task. SPIRIT-CONSORT-ELM provides a benchmark for evaluating reporting guideline completeness at the element level, enabling assessment of RCT transparency beyond the simple presence or absence of checklist items and is publicly available at https://osf.io/kznx4/ . The automated pipeline establishes a robust baseline for assessing RCT reporting and demonstrates potential as a practical aid for authors, reviewers, and editors to identify and address gaps in completeness and transparency of RCT reports.