arXiv subjects

Beibei Li

Publications and source records attributed to Beibei Li.

45 records · Page 3Linked to original sources

arXiv2022

Improving Micro-video Recommendation via Contrastive Multiple Interests

With the rapid increase of micro-video creators and viewers, how to make personalized recommendations from a large number of candidates to viewers begins to attract more and more attention. However, existing micro-video recommendation models rely on expensive multi-modal information and learn an overall interest embedding that cannot reflect the user's multiple interests in micro-videos. Recently, contrastive learning provides a new opportunity for refining the existing recommendation techniques. Therefore, in this paper, we propose to extract contrastive multi-interests and devise a micro-video recommendation model CMI. Specifically, CMI learns multiple interest embeddings for each user from his/her historical interaction sequence, in which the implicit orthogonal micro-video categories are used to decouple multiple user interests. Moreover, it establishes the contrastive multi-interest loss to improve the robustness of interest embeddings and the performance of recommendations. The results of experiments on two micro-video datasets demonstrate that CMI achieves state-of-the-art performance over existing baselines.

cs.IR↗

arXiv2022

Uncovering the Source of Machine Bias

We develop a structural econometric model to capture the decision dynamics of human evaluators on an online micro-lending platform, and estimate the model parameters using a real-world dataset. We find two types of biases in gender, preference-based bias and belief-based bias, are present in human evaluators' decisions. Both types of biases are in favor of female applicants. Through counterfactual simulations, we quantify the effect of gender bias on loan granting outcomes and the welfare of the company and the borrowers. Our results imply that both the existence of the preference-based bias and that of the belief-based bias reduce the company's profits. When the preference-based bias is removed, the company earns more profits. When the belief-based bias is removed, the company's profits also increase. Both increases result from raising the approval probability for borrowers, especially male borrowers, who eventually pay back loans. For borrowers, the elimination of either bias decreases the gender gap of the true positive rates in the credit risk evaluation. We also train machine learning algorithms on both the real-world data and the data from the counterfactual simulations. We compare the decisions made by those algorithms to see how evaluators' biases are inherited by the algorithms and reflected in machine-based decisions. We find that machine learning algorithms can mitigate both the preference-based bias and the belief-based bias.

cs.LG↗

arXiv2021

A Behavior-aware Graph Convolution Network Model for Video Recommendation

Interactions between users and videos are the major data source of performing video recommendation. Despite lots of existing recommendation methods, user behaviors on videos, which imply the complex relations between users and videos, are still far from being fully explored. In the paper, we present a model named Sagittarius. Sagittarius adopts a graph convolutional neural network to capture the influence between users and videos. In particular, Sagittarius differentiates between different user behaviors by weighting and fuses the semantics of user behaviors into the embeddings of users and videos. Moreover, Sagittarius combines multiple optimization objectives to learn user and video embeddings and then achieves the video recommendation by the learned user and video embeddings. The experimental results on multiple datasets show that Sagittarius outperforms several state-of-the-art models in terms of recall, unique recall and NDCG.

cs.CV↗

arXiv2021

AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack

Recent studies have revealed the vulnerability of graph convolutional networks (GCNs) to edge-perturbing attacks, such as maliciously inserting or deleting graph edges. However, a theoretical proof of such vulnerability remains a big challenge, and effective defense schemes are still open issues. In this paper, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks. Following this, an anonymous graph convolutional network, named AN-GCN, is proposed to counter against edge-perturbing attacks. Specifically, we present a node localization theorem to demonstrate how the GCN locates nodes during its training phase. In addition, we design a staggered Gaussian noise based node position generator, and devise a spectral graph convolution based discriminator in detecting the generated node positions. Further, we give the optimization of the above generator and discriminator. AN-GCN can classify nodes without taking their position as input. It is demonstrated that the AN-GCN is secure against edge-perturbing attacks in node classification tasks, as AN-GCN classifies nodes without the edge information and thus makes it impossible for attackers to perturb edges anymore. Extensive evaluations demonstrated the effectiveness of the general edge-perturbing attack model in manipulating the classification results of the target nodes. More importantly, the proposed AN-GCN can achieve 82.7% in node classification accuracy without the edge-reading permission, which outperforms the state-of-the-art GCN.

cs.LG↗

arXiv2021

What Makes People Install a COVID-19 Contact-Tracing App? Understanding the Influence of App Design and Individual Difference on Contact-Tracing App Adoption Intention

Smartphone-based contact-tracing apps are a promising solution to help scale up the conventional contact-tracing process. However, low adoption rates have become a major issue that prevents these apps from achieving their full potential. In this paper, we present a national-scale survey experiment ($N = 1963$) in the U.S. to investigate the effects of app design choices and individual differences on COVID-19 contact-tracing app adoption intentions. We found that individual differences such as prosocialness, COVID-19 risk perceptions, general privacy concerns, technology readiness, and demographic factors played a more important role than app design choices such as decentralized design vs. centralized design, location use, app providers, and the presentation of security risks. Certain app designs could exacerbate the different preferences in different sub-populations which may lead to an inequality of acceptance to certain app design choices (e.g., developed by state health authorities vs. a large tech company) among different groups of people (e.g., people living in rural areas vs. people living in urban areas). Our mediation analysis showed that one's perception of the public health benefits offered by the app and the adoption willingness of other people had a larger effect in explaining the observed effects of app design choices and individual differences than one's perception of the app's security and privacy risks. With these findings, we discuss practical implications on the design, marketing, and deployment of COVID-19 contact-tracing apps in the U.S.

cs.HC↗

arXiv2021

Improving Sequential Recommendation with Attribute-augmented Graph Neural Networks

Many practical recommender systems provide item recommendation for different users only via mining user-item interactions but totally ignoring the rich attribute information of items that users interact with. In this paper, we propose an attribute-augmented graph neural network model named Murzim. Murzim takes as input the graphs constructed from the user-item interaction sequences and corresponding item attribute sequences. By combining the GNNs with node aggregation and an attention network, Murzim can capture user preference patterns, generate embeddings for user-item interaction sequences, and then generate recommendations through next-item prediction. We conduct extensive experiments on multiple datasets. Experimental results show that Murzim outperforms several state-of-the-art methods in terms of recall and MRR, which illustrates that Murzim can make use of item attribute information to produce better recommendations. At present, Murzim has been deployed in MX Player, one of India's largest streaming platforms, and is recommending videos for tens of thousands of users.

cs.IR↗

arXiv2021

Empowering Patients Using Smart Mobile Health Platforms: Evidence From A Randomized Field Experiment

With today's technological advancements, mobile phones and wearable devices have become extensions of an increasingly diffused and smart digital infrastructure. In this paper, we examine mobile health (mHealth) platforms and their health and economic impacts on the outcomes of chronic disease patients. We partnered with a major mHealth firm that provides one of the largest mHealth apps in Asia specializing in diabetes care. We designed a randomized field experiment based on detailed patient health activities (e.g., exercises, sleep, food intake) and blood glucose values from 1,070 diabetes patients over several months. We find the adoption of the mHealth app leads to an improvement in health behavior, which leads to both short term metrics (reduction in patients' blood glucose and glycated hemoglobin levels) and longer-term metrics (hospital visits and medical expenses). Patients who adopted the mHealth app undertook more exercise, consumed healthier food, walked more steps and slept for longer times. They also were more likely to substitute offline visits with telehealth. A comparison of mobile vs. PC version of the same app demonstrates that mobile has a stronger effect than PC in helping patients make these behavioral modifications with respect to diet, exercise and lifestyle, which leads to an improvement in their healthcare outcomes. We also compared outcomes when the platform facilitates personalized health reminders to patients vs. generic reminders. Surprisingly, we find personalized mobile messages with patient-specific guidance can have an inadvertent (smaller) effect on patient app engagement and lifestyle changes, leading to a lower health improvement. However, they are more like to encourage a substitution of offline visits by telehealth. Overall, our findings indicate the massive potential of mHealth technologies and platform design in achieving better healthcare outcomes.

econ.GN↗

arXiv2020

What Makes a Star Teacher? A Hierarchical BERT Model for Evaluating Teacher's Performance in Online Education

Education has a significant impact on both society and personal life. With the development of technology, online education has been growing rapidly over the past decade. While there are several online education studies on student behavior analysis, the course concept mining, and course recommendations (Feng, Tang, and Liu 2019; Pan et al. 2017), there is little research on evaluating teachers' performance in online education. In this paper, we conduct a systematic study to understand and effectively predict teachers' performance using the subtitles of 1,085 online courses. Our model-free analysis shows that teachers' verbal cues (e.g., question strategy, emotional appealing, and hedging) and their course structure design are both significantly correlated with teachers' performance evaluation. Based on these insights, we then propose a hierarchical course BERT model to predict teachers' performance in online education. Our proposed model can capture the hierarchical structure within each course as well as the deep semantic features extracted from the course content. Experiment results show that our proposed method achieves significant gain over several state-of-the-art methods. Our study provides a significant social impact in helping teachers improve their teaching style and enhance their instructional material design for more effective online teaching in the future.

cs.LG↗

arXiv2020

Trading Privacy for the Greater Social Good: How Did America React During COVID-19?

Digital contact tracing and analysis of social distancing from smartphone location data are two prime examples of non-therapeutic interventions used in many countries to mitigate the impact of the COVID-19 pandemic. While many understand the importance of trading personal privacy for the public good, others have been alarmed at the potential for surveillance via measures enabled through location tracking on smartphones. In our research, we analyzed massive yet atomic individual-level location data containing over 22 billion records from ten Blue (Democratic) and ten Red (Republican) cities in the U.S., based on which we present, herein, some of the first evidence of how Americans responded to the increasing concerns that government authorities, the private sector, and public health experts might use individual-level location data to track the COVID-19 spread. First, we found a significant decreasing trend of mobile-app location-sharing opt-out. Whereas areas with more Democrats were more privacy-concerned than areas with more Republicans before the advent of the COVID-19 pandemic, there was a significant decrease in the overall opt-out rates after COVID-19, and this effect was more salient among Democratic than Republican cities. Second, people who practiced social distancing (i.e., those who traveled less and interacted with fewer close contacts during the pandemic) were also less likely to opt-out, whereas the converse was true for people who practiced less social-distancing. This relationship also was more salient among Democratic than Republican cities. Third, high-income populations and males, compared with low-income populations and females, were more privacy-conscientious and more likely to opt-out of location tracking.

econ.EM↗