A5102899038- Recommender Systems and Techniques
- Mobile Crowdsensing and Crowdsourcing
- Expert finding and Q&A systems
- Advanced Decision-Making Techniques
- Advanced Bandit Algorithms Research
- Topic Modeling
- Sentiment Analysis and Opinion Mining
- Image Retrieval and Classification Techniques
- Text and Document Classification Technologies
- Brain Tumor Detection and Classification
- Digital Communication and Language
- Advanced Sensor and Control Systems
- Industrial Technology and Control Systems
- Cardiac Arrhythmias and Treatments
- Atrial Fibrillation Management and Outcomes
- Aluminum toxicity and tolerance in plants and animals
- Imbalanced Data Classification Techniques
- Visual Attention and Saliency Detection
- Text Readability and Simplification
- Information Retrieval and Search Behavior
- Internet Traffic Analysis and Secure E-voting
- Stochastic Gradient Optimization Techniques
- Silicon Effects in Agriculture
- Linguistics, Language Diversity, and Identity
- Privacy, Security, and Data Protection
Hangzhou Dianzi University
2025
South China Agricultural University
2024
Google (United States)
2023-2024
Fu Wai Hospital
2023
Chinese Academy of Medical Sciences & Peking Union Medical College
2022-2023
State Key Laboratory of Cardiovascular Disease
2023
University of Minnesota System
2021
Beijing University of Posts and Telecommunications
2020
Beijing Information Science & Technology University
2020
State Key Laboratory of Remote Sensing Science
2020
Community Question Answering (CQA) services thrive as a result of small number highly active users, typically called experts, who provide large high quality useful answers. Understanding the temporal dynamics and interactions between experts can present key insights into how community members evolve over time. In this paper, we study in CQA analyze changes their behavioral patterns Further, using unsupervised machine learning methods, show interesting evolution that help us distinguish from...
Explanations are important for users to make decisions on whether take recommendations. However, algorithm generated explanations can be overly simplistic and unconvincing. We believe that humans overcome these limitations. Inspired by how people explain word-of-mouth recommendations, we designed a process, combining crowdsourcing computation, generates personalized natural language explanations. modeled key topical aspects of movies, asked crowdworkers write based quotes from online movie...
Emoji are commonly used in modern text communication. However, as graphics with nuanced details, emoji may be open to interpretation. also render differently on different viewing platforms (e.g., Apple’s iPhone vs. Google’s Nexus phone), potentially leading communication errors. We explore whether renderings or differences across give rise diverse interpretations of emoji. Through an online survey, we solicit people’s a sample the most popular characters, each rendered for multiple...
The essence of a recommender system is that it can recommend items personalized to the preferences an individual user. But typically users are given no explicit control over this personalization, and instead left guessing about how their actions affect resulting recommendations. We hypothesize any algorithm will better fit some users' expectations than others, leaving opportunities for improvement. To address challenge, we study puts in hands users. Specifically, build evaluate incorporates...
Community Question Answering (CQA) service enables its users to exchange knowledge in the form of questions and answers. By allowing contribute knowledge, CQA not only satisfies question askers but also provides valuable references other with similar queries. Due a large volume questions, all get fully answered. As result, it can be useful route potential answerer. In this paper, we present routing scheme which takes into account answering, commenting voting propensities users. Unlike prior...
As users browse a recommender system, they systematically consider or skip over much of the displayed content. It seems obvious that these eye gaze patterns contain rich signal concerning users' preferences. However, because tracking data is not available to most systems, signals are widely incorporated into personalization models. In this work, we show it possible predict by combining easily-collected user browsing with from small number in grid-based interface. Our technique able leverage...
To achieve high quality initial personalization, recommender systems must provide an efficient and effective process for new users to express their preferences. We propose that this goal is best served not by the classical method where begin expressing preferences individual items - inefficient way convert a user's effort into improved personalization. Rather, we can groups of items. test idea designing evaluating interactive across are automatically generated clustering algorithms....
Recommender systems are essential for finding personalized content users on online platforms. These often trained historical user interaction data, which collects feedback system recommendations. This creates a loop leading to popularity bias; popular is over-represented in the better learned, and thus recommended even more. Less struggles reach its potential audiences. Popularity bias limits diversity of that exposed to, makes it harder new creators gain traction. Existing methods alleviate...
A relatively new feature in Google Play Store presents mobile app search results grouped by topic, helping users to quickly navigate and explore. The underlying Search Results Clustering (SRC) system faces several challenges, including grouping topical coherent clusters as well finding the appropriate level of granularity for clustering. We present AppGrouper, an alternative approach algorithmic-only solutions, incorporating human input a knowledge-graph-based clustering process. AppGrouper...
Online search and item recommendation systems are often based on being able to correctly label items with topical keywords. Typically, labelers analyze the main text associated item, but social media posts multimedia in nature contain contents beyond text. Topic labeling for is therefore an important open problem supporting effective recommendation. In this work, we present a novel solution Google+ posts, which integrated number of different entity extractors annotators, each responsible...
Sequential recommenders have been widely used in industry due to their strength modeling user preferences. While these models excel at learning a user's positive interests, less attention has paid from negative feedback. Negative feedback is an important lever of control, and comes with expectation that should respond quickly reduce similar recommendations the user. However, signals are often ignored training objective sequential retrieval models, which primarily aim predicting interactions....
Software defect prediction (SDP) is an effective technique to lower software module testing costs. However, the imbalanced distribution almost exists in all SDP datasets and restricts accuracy of prediction. In order balance data reasonably, we propose a novel resampling method LIMCR on basis Naïve Bayes optimize improve performance. The main idea remove less-informative majorities for rebalancing after evaluating degree being informative every sample from majority class. We employ 29...
The fast developing social network is a double-edged sword. It remains serious problem to provide users with excellent mobile services as well protecting privacy data. Most popular applications utilize behavior of build connection people having similar behavior, thus improving user experience. However, many do not want share their certain behavioral information the recommendation system. In this paper, we aim design secure friend system based on called PRUB. proposed aims at achieving...
Alzheimer's Disease (AD) is a complex neurodegenerative disorder marked by memory loss, executive dysfunction, and personality changes. Early diagnosis challenging due to subtle symptoms varied presentations, often leading misdiagnosis with traditional unimodal diagnostic methods their limited scope. This study introduces an advanced multimodal classification model that integrates clinical, cognitive, neuroimaging, EEG data enhance accuracy. The incorporates feature tagger tabular coding...
The ACM RecSys'18 Late-Breaking Results track (previously known as the Poster track) is part of main program 2018 Conference on Recommender Systems in Vancouver, Canada. attracted 48 submissions this year out which 18 papers could be accepted resulting an acceptance rated 37.5%.
Due to the excellent feature learning and representation capabilities of deep learning, method based on for mobile phone screen defect detection is gradually being applied industrial detection. Nowadays, cross-entropy loss commonly used in only focuses d