Serina Chang @serinachang5 Twitter profile | Pikagi

Pikagi

Serina Chang

@serinachang5

1,949

Followers

383

Following

24

Media

230

Statuses

On the 2023-2024 academic job market | CS PhD candidate at Stanford, advised by @jure and @jugander . Networks, ML, public health, computational social science.

https://t.co/YGOdBKIZbX

Joined December 2016

Don't wanna be here? Send us removal request.

Pinned Tweet

@serinachang5

Serina Chang

7 months

I’m on the academic job market! I’ll have a PhD from @Stanford CS in 2024. My research develops ML + network science methods to tackle complex societal challenges, from pandemics to polarization to supply chains. See my website + research statement for details! Highlights below:

22

130

810

Last Seen Profiles

@CappiSydne22517

@ohsgswimdive

@_chartstan

@mahou_michi

@NJ2AS

@stw_pdg

@joepohlen

@Uwambajemariya6

@alexander_nanci

@Burn1nmyl1ght

@zxqwe12_

@mgcipo

@FMGSuite

@TiiMariie

@Ayane_mc

@Chrisssmustang

@1chan_meijin

@ClifMarshall

@AnnWalk21456111

@jandakembangstw

@FranceenUkraine

@Apexerkarma

@Flaminiesta

@CHSHogCaller

@govochto

@Annakwood

@lactual

@FanDuelCanada

@FernyVonDoll

@EliasToufexis

@ChristianSaaCS

@Bucktonbirder

@EKripperino

@ASNRehab

@CheetahsRugby

@BASEBALLGL

@serinachang5

Serina Chang

3 years

So excited to announce that we won the KDD 2021 Best Paper Award in the Applied Data Science track for our paper, "Supporting COVID-19 policy response with large-scale mobility-based modeling”!

Tweet media one

11

33

311

@serinachang5

Serina Chang

4 years

Check out our new paper in @nature , “Mobility network models of COVID-19 explain inequities and inform reopening”! @2plus2make5 @PangWeiKoh @jalinegerardin @beth_redbird @davidgrusky @jure 1/9

16

85

256

@serinachang5

Serina Chang

2 years

Very honored to receive the @MetaAI PhD fellowship in Computational Social Science!! Thank you to my incredible advisors @jure and @jugander , mentors, and collaborators for your brilliance and support :)

@jure

Jure Leskovec

2 years

Congrats to @serinachang5 for winning the Meta PhD Fellowship in Computational Social Science!! Serina has done amazing work modeling the spread of COVID on large-scale human mobility networks and applying this research to real-world impact.

1

14

127

4

6

127

@serinachang5

Serina Chang

11 months

📢 Excited to announce a new paper with @erichorvitz and @adamfourney : “Accurate Measures of Vaccination and Concerns of Vaccine Holdouts from Web Search Logs” @MSFTResearch 1/ Paper: Data & code:

4

27

91

@serinachang5

Serina Chang

1 year

Excited to announce new work to appear at @RealAAAI '23! We study the problem of geographic spillovers, where people cross county/state borders to circumvent local restrictions (think: COVID lockdowns, gun control). Joint work w @dvrabac , @jure , @jugander :

Tweet media one

3

14

81

@serinachang5

Serina Chang

2 years

Excited to attend @icwsm in person this week!! I’ll be presenting joint work with @jugander on Thu June 9 (Session 4). We often discuss the impacts of recommender systems on society, but relative to what counterfactual - how would user outcomes change in a world without them? 1/5

1

10

74

@serinachang5

Serina Chang

2 years

Just arrived in Seattle for @MSFTResearch intern week! Excited to be working with @erichorvitz and @adamfourney this summer on projects using search queries to investigate the effects of COVID policy interventions on dynamic behavior (eg, vaccine uptake, mobility patterns). 1/2

2

1

67

@serinachang5

Serina Chang

4 years

Our model also predicts that 10% of POIs account for over 80% of infections at POIs. Restaurants, gyms, hotels, and cages are among the riskiest categories to reopen. These places are riskier because they tend to have higher visitor densities and/or visitors stay longer. 5/9

Tweet media one

7

30

55

@serinachang5

Serina Chang

4 years

Very excited to share this new work! We build an epidemiological model on top of a fine-grained (hourly) mobility network, and analyze the impacts of reopening + how socioeconomic / racial disparities in infections can arise from mobility patterns alone.

@jure

Jure Leskovec

4 years

Mobility network modeling explains higher SARS-CoV-2 infection rates among disadvantaged groups and informs reopening strategies. Joint work with @serinachang5 @2plus2make5 PangWeiKoh @jalinegerardin @beth_redbird @davidgrusky

Tweet media one

1

58

176

0

14

55

@serinachang5

Serina Chang

2 years

Such a joy to work w/ @dallascard and the rest of our amazing interdisciplinary team! Combining NLP + domain expertise, we conduct the first comprehensive quantitative analysis of Congressional speeches about immigration and characterize dramatic changes in discourse over 140 yrs

@dallascard

Dallas Card

2 years

Excited to share that our paper on the history of immigration discourse in congress has now been published (open access) in PNAS!

Tweet media one

12

142

567

0

5

52

@serinachang5

Serina Chang

8 months

Excited to be attending @Cornell 's Future Faculty Symposium this week in Ithaca, NY!! Thanks to Cornell for organizing this fantastic event - I'm looking forward to spending time with the amazing faculty and the other symposium scholars!

1

5

42

@serinachang5

Serina Chang

3 years

Super interesting opinion piece by @iarynam which dives into our COVID model’s findings around capacity caps and socioeconomic disparities in the first wave of the pandemic. Love these gorgeous graphics; I’m definitely taking notes for my next data viz 😍

Tweet card media

Opinion | The Magic Number for Reducing Infections and Keeping Businesses Open (Published 2020)

Data from early in the pandemic reveals there’s a “sweet spot.”

www.nytimes.com

2

3

30

@serinachang5

Serina Chang

7 months

Three fundamental challenges arise from these gaps: (1) How to infer networks from aggregated, noisy, or incomplete data (2) How to extract precise behavioral signals from vast unlabeled data (3) How to estimate causal effects (eg, of policies) from observational network data

1

0

26

@serinachang5

Serina Chang

3 years

1/ New preprint! Excited to introduce follow-up work on our @nature paper: we extended our COVID model and turned it into a decision-support tool that can directly help policymakers in the remaining (hopefully few!) months of COVID response:

Tweet card media

Supporting COVID-19 policy response with large-scale mobility-based modeling

Social distancing measures, such as restricting occupancy at venues, have been a primary intervention for controlling the spread of COVID-19. However, these mobility restrictions place a significant...

www.medrxiv.org

1

7

25

@serinachang5

Serina Chang

4 years

Check out the interactive simulation on our website () to learn more! Special thanks to @jdzamfi , @MarkWhiting , @jwkritchie , and @msbernst for building out the simulation frontend. 9/9

Tweet media one

3

2

24

@serinachang5

Serina Chang

1 year

The deadline is coming up soon: submit your work to the Data Science for Social Good Workshop at KDD'23! Co-organized with @AmulyaYadav19 @AyanMukhrjee and Aparna Taneja Deadline: June 5, 2023 Workshop: August 7, 2023 (Long Beach, CA)

1

11

23

@serinachang5

Serina Chang

7 months

Second: I’ve built ML systems to extract precise behavioral signals from unlabeled data - eg, GNNs to detect vaccine intent from search logs (w/ @adamfourney @erichorvitz ), LLMs to study immigration attitudes from political speeches (PNAS’22 w/ @dallascard @jcbecker_econ et al)

1

5

22

@serinachang5

Serina Chang

4 years

We identify two mechanisms driving these disparities: (1) disadvantaged groups were not able to reduce their mobility as much in Mar 2020, (2) the POIs that disadvantaged groups visit tend to be more crowded, which increases risk of infection. 7/9

Tweet media one

1

6

20

@serinachang5

Serina Chang

9 months

I'm attending #KDD2023 ! On Aug 7, I'll be - running the Data Science for Social Good Workshop: - presenting work w @erichorvitz @adamfourney on search logs + vaccines at @EpidamikW (4:10-4:50pm): - moderating a panel at KDD EDI day

1

2

20

@serinachang5

Serina Chang

7 months

Third: I’ve developed methods blending causal inference+graph ML to discover causal mechanisms of dynamic networks - eg, RDD-based methods to estimate spillovers in mobility networks (AAAI’23 w/ @dvrabac @jure @jugander ), GNNs to learn production functions from supply chains

1

0

19

@serinachang5

Serina Chang

7 months

My work is also recognized by @NSF GRFP, @Meta PhD Fellowship, EECS Rising Stars, and Rising Stars in Data Science. Beyond research, I’m passionate about teaching, mentorship, service - I’m currently Program Chair for ML for Health 2023 and mentoring four talented undergrads :)

1

0

20

@serinachang5

Serina Chang

7 months

On the first challenge: in our Nature paper (w/ @2plus2make5 @PangWeiKoh et al), we developed methods to infer mobility networks (5.4B hourly edges!) from aggregated location data and modeled the spread of COVID-19 with unprecedented granularity, informing reopening + disparities

1

0

20

@serinachang5

Serina Chang

7 months

I would love to hear about any opportunities that might be a good fit!! You can find my contact info on my website, along with my CV and research statement:

6

0

20

@serinachang5

Serina Chang

4 years

Based on mobility data *alone*, the model correctly predicts that lower-income and less white neighborhoods are infected at higher rates. These disparities in COVID infection rates are well-reported, but this suggests that mobility may be a strong contributing factor. 6/9

1

1

18

@serinachang5

Serina Chang

7 months

I leverage novel high-frequency data sources to capture human networks + behaviors at the center of societal challenges. These data provide new opportunities to capture networks + behaviors at scale BUT there remain large gaps between real-world systems and data…

1

0

19

@serinachang5

Serina Chang

3 years

We built a novel computational tool for policymakers to assess tradeoffs between thousands of potential mobility measures and predicted COVID-19 infections. Check out our recent blog post for details:

Tweet card media

Supporting COVID-19 policy response with large-scale mobility-based modeling

A novel computational tool for policymakers to assess the impacts of thousands of different mobility measures on predicted COVID-19 infections, helping them to navigate difficult tradeoffs between...

ai.stanford.edu

1

4

18

@serinachang5

Serina Chang

1 year

I'm presenting this work at @RealAAAI this week (Saturday 2/11 poster session)! Please reach out if you're in DC and want to chat!!

@serinachang5

Serina Chang

1 year

Excited to announce new work to appear at @RealAAAI '23! We study the problem of geographic spillovers, where people cross county/state borders to circumvent local restrictions (think: COVID lockdowns, gun control). Joint work w @dvrabac , @jure , @jugander :

Tweet media one

3

14

81

1

1

18

@serinachang5

Serina Chang

7 months

Finally, a central pillar of my research is closing the loop. I’ve deployed decision-support tools, including a dashboard enabling public health officials to assess the potential impacts of thousands of reopening plans - this work (w/ @UVA_BI ) won the Best Paper Award in KDD'21🏆

1

2

17

@serinachang5

Serina Chang

7 months

By closing these gaps, we can derive key insights and build decision-support tools, paving a new way for *human-centered decision-making* powered by large-scale computation and data 🎆

1

1

17

@serinachang5

Serina Chang

3 years

Thank you and congrats to my incredible collaborators from Stanford, @UVA_BI , and Northwestern - @wilson_mandy , Bryan Lewis, Zakaria Mehrab, Komal Dudakiya, @2plus2make5 , @PangWeiKoh , @jalinegerardin , Beth Redbird, @davidgrusky , Madhav Marathe, and @jure !

1

2

16

@serinachang5

Serina Chang

4 years

Our results highlight the need for policy-makers to consider the impacts of reopening on different populations. By supporting detailed, data-driven analyses, we hope that our model can help to address this need and inform more effective and equitable responses to COVID-19. 8/9

1

1

13

@serinachang5

Serina Chang

3 years

Had a wonderful time chatting with @katakeith and @lucy3_li about our work on mobility network models of COVID! Check out the episode here: we discuss the origins of this interdisciplinary project, and the joys and challenges of working on a high-stakes issue in near real-time.

@katakeith

Katie Keith

3 years

Listen to @serinachang5 talk about her use of cellphone data to track COVID-19 mobility dynamics and the challenges of communicating this science to the public on Eps.4 of @lucy3_li and my podcast: Diaries of Social Data Research!

0

2

8

0

3

12

@serinachang5

Serina Chang

11 months

#KDD2023 Data Science for Social Good Workshop deadline extended to June 12!! We encourage a wide range of work, from perspectives to methods to applications in health, sustainability, etc. See CFP: @AmulyaYadav19 @AyanMukhrjee and Aparna Taneja

Data Science for Social Good at KDD 2023

In this workshop, we invite the research community in data science for social good to submit papers for DSSG workshop at KDD 23.

kdd-dssg.github.io

@serinachang5

Serina Chang

1 year

The deadline is coming up soon: submit your work to the Data Science for Social Good Workshop at KDD'23! Co-organized with @AmulyaYadav19 @AyanMukhrjee and Aparna Taneja Deadline: June 5, 2023 Workshop: August 7, 2023 (Long Beach, CA)

1

11

23

0

5

10

@serinachang5

Serina Chang

7 months

Excited to be giving a talk at the @Stanford Graph Learning Workshop next week! I'll be presenting with Qi Xiu from @Hitachi on developing temporal GNNs to model global supply chains🚢➡️🚚➡️📦 Register here:

Stanford Graph Learning Workshop 2023

Stanford Graph Learning Workshop

snap.stanford.edu

@jure

Jure Leskovec

7 months

🌟 Announcing the speakers for the Stanford Graph Learning Workshop 2023 on Oct 24 2023!🤝 Bringing together academia & industry leaders to delve into advances in #MachineLearning & #AI in Relational domains, Foundation models, and Multimodal AI. 📢 Register at:

Tweet media one

4

58

258

0

7

10

@serinachang5

Serina Chang

7 months

@lilyxu0 is an exceptional researcher, not to mention amazing organizer, mentor, and friend. Her work on AI, conservation, and health has inspired me throughout my PhD. Hire her!!

@lilyxu0

Lily Xu

7 months

I'm on the academic job market! I'm a PhD student at @Harvard , where I develop and deploy AI decision-making techniques for planetary health. My research enables practitioners to take efficient, robust actions necessary in these high-stakes, low-data settings.

Tweet media one

19

117

582

0

1

11

@serinachang5

Serina Chang

4 years

We find that reduced occupancy reopening — ie, reopening but capping each POI's max occupancy — is effective. In Chicago, our model predicts that capping at 20% occupancy reduces infections by more than 80% but only loses around 40% of POI visits, compared to fully reopening. 4/9

Tweet media one

1

2

11

@serinachang5

Serina Chang

4 years

Using anonymized, aggregated location data from @SafeGraph , we construct mobility networks that capture the hourly movements of people from neighborhoods to points-of-interest (POIs) like restaurants and gyms. Our networks cover 553k POIs and 98M people from Mar-May 2020. 2/9

Tweet media one

1

1

11

@serinachang5

Serina Chang

9 months

@jure Huge congrats, @jure !!! Well deserved!

0

0

0

@serinachang5

Serina Chang

3 years

2/ Thanks to our @UVA_BI collaborators @wilson_mandy , Bryan Lewis, Zakaria Mehrab, Komal Dudakiya & Madhav Marathe, who've long been supporting VA Dept of Health, and my Stanford/Northwestern coauthors @2plus2make5 , @PangWeiKoh , @jalinegerardin , Beth Redbird, @davidgrusky & @jure

2

2

8

@serinachang5

Serina Chang

2 years

Even though the models are identical in process, this reversal in perspective results in dramatic differences! Through theorems + experiments, we show that these differences are pervasive across a large class of “recommender” and “organic” models (). 4/5

2

0

7

@serinachang5

Serina Chang

4 years

Thanks for the great interview! Check out our full paper at .

Tweet card media

Mobility network models of COVID-19 explain inequities and inform reopening

Nature - An epidemiological model that integrates fine-grained mobility networks illuminates mobility-related mechanisms that contribute to higher infection rates among disadvantaged socioeconomic...

@Stanford

Stanford University

4 years

A Stanford team has created a model to help identify effective and equitable reopening policies. To do it, they traced the footsteps of 98 million Americans through half a million establishments in 10 of the country's largest metropolitan areas: #COVID19

3

17

76

0

2

6

@serinachang5

Serina Chang

10 months

Fascinating study about the science of LLM science by @2plus2make5 and team! Check out their awesome results ⬇️ and awesome graphics :)

@2plus2make5

Emma Pierson

10 months

New working paper quantifying arXiv publication patterns in the age of LLMs! Joint work with @rajivmovva , @sidhikab1 , @kennylpeng , @gsagostini , and @NikhGarg . We analyze LLM citation patterns, fastest growing topics, many other things. Some of our findings: 1/N

6

35

148

0

0

6

@serinachang5

Serina Chang

4 years

@estebanmoro @tiagopeixoto @tinaeliassi @mattk7 @leoferres @svscarpino @jkbren @SafeGraph @jure @tinaeliassi - thanks for looking at the paper closely (and noting IRB exemption)! Our modeled pop dropped by 7M bc, following some new info from SafeGraph, we modified how we filtered POIs, which shrunk the set of CBGs that visited these POIs frequently enough to be included.

1

0

6

@serinachang5

Serina Chang

2 years

Come say hi if you're interested in this work or modeling complex social systems at large! Much of my current research also involves modeling diffusion processes (eg, COVID) over large-scale networks and developing methods to effectively intervene on complex systems. 5/5

1

0

6

@serinachang5

Serina Chang

4 years

Thanks Steffanie!! Special shoutout to all the amazing women I got to work with on this project @2plus2make5 @jalinegerardin @beth_redbird 😍

@chngin_the_wrld

Steffanie Strathdee, PhD 🗡️ 🦠Superbug Slayer🗡️

@chngin_the_wrld

4 years

Today's #shoutout to #womenInSTEM goes to @serinachang5 for her awesome paper @nature showing how mobility networks predict #COVID19 transmission & can inform re-opening. w/ @2plus2make5 @PangWeiKoh @jalinegerardin @beth_redbird @davidgrusky @jure

0

8

26

0

0

6

@serinachang5

Serina Chang

4 years

@dpPTPhD Ah thank you for catching that! Yes cafes, definitely not cages.

1

0

3

@serinachang5

Serina Chang

4 years

@estebanmoro @tiagopeixoto @tinaeliassi @mattk7 @leoferres @svscarpino @jkbren @SafeGraph @jure Chiming in here - thank you all for engaging with our work! Agreed that there are important discussions to be had around data tracking. In this work tho, as @mattk7 , @leoferres , and @estebanmoro noted, we use anonymized + aggregated location data in hopes of preserving privacy.

1

0

5

@serinachang5

Serina Chang

1 year

You can find our code + materials to run your own RDD experiment on the CA Blueprint at . Please reach out if you have thoughts or find me at @RealAAAI in Feb! Thanks also to @2plus2make5 for helpful discussions + @CAPublicHealth for great documentation 9/

Tweet card media

GitHub - snap-stanford/covid-spillovers

Contribute to snap-stanford/covid-spillovers development by creating an account on GitHub.

0

0

5

@serinachang5

Serina Chang

4 years

By overlaying a simple SEIR model on these networks, we're able to capture the broad relationship between mobility and disease spread. This allows us to assess a variety of reopening questions: which places are the riskiest to reopen? when/how should we reopen? 3/9

Tweet media one

1

1

5

@serinachang5

Serina Chang

3 years

See our recent paper for details on the study -- this is joint work with my brilliant co-first authors @2plus2make5 and @PangWeiKoh , and senior authors @beth_redbird , @jalinegerardin , @davidgrusky , and @jure .

Tweet card media

Mobility network models of COVID-19 explain inequities and inform reopening

Nature - An epidemiological model that integrates fine-grained mobility networks illuminates mobility-related mechanisms that contribute to higher infection rates among disadvantaged socioeconomic...

0

0

5

@serinachang5

Serina Chang

1 year

So: spillovers exist, they do undermine local policies, but intermediate strategies (when optimized) can achieve a good balance btwn policy efficacy and flexibility! Lots more to explore here: eg, other spillover domains (content moderation!) and tradeoff dimensions 8/

1

0

4

@serinachang5

Serina Chang

11 months

See our paper for many more analyses: Check out our vaccine intent estimates + ontology: Special thanks to @2plus2make5 , @jugander , @jure , @yusufroohani , @krisgligoric , @LisaCooperMD and others for helpful comments and support!! 13/

0

0

4

@serinachang5

Serina Chang

7 months

@navaneethsan @Stanford Thank you!! I'm primarily interested in academic positions since I'd like to establish my own lab and mentor students, but I'm super interested in translating research into industry + policy impact and have really enjoyed past collabs! (eg, with Microsoft and Hitachi)

0

0

2

@serinachang5

Serina Chang

1 year

Yes! We estimate these effects on a large-scale mobility network w billions of dynamic edges (using loss-corrected negative sampling to fit our model). We find *significant spillover movement* from the purple to red tier, with larger effects in retail, eating places, and gyms 5/

Tweet media one

1

0

4

@serinachang5

Serina Chang

2 years

Please reach out if you’re in the area / would like to chat about related ideas! I’ll also be in NYC for the rest of the summer :) 2/2

1

0

4

@serinachang5

Serina Chang

1 year

In our work, we can make unconfounded estimates of spillovers! We identify an ideal setting: CA Blueprint for a Safer Economy, where counties were assigned each week to "tiers" of varying restrictiveness, eg, in purple (most extreme), restaurants + gyms were outdoors only 3/

Tweet media one

1

0

4

@serinachang5

Serina Chang

1 year

We’re now able to quantify how spillovers introduce tradeoffs for policymaking across spatial scales. Contrasting local + global regimes, our spillover estimates suggest that county-level restrictions are only 54% as effective as statewide restrictions at reducing mobility! 6/

1

0

4

@serinachang5

Serina Chang

2 years

The key to our models is a reversal in perspective: the user knows her own interests well but needs to estimate item attributes from noisy samples (eg, movie trailers) while the recsys knows items well but needs to estimate (new) user interests from noisy samples. 3/5

1

0

4

@serinachang5

Serina Chang

11 months

Using the classifier, we can estimate vaccine intent rates down to ZIP code tabulation areas, around 10x the granularity of counties! With search signals, we can also detect vaccine intent in *real time*: we find that the CDC’s time series lags ours by 7-15 days. 7/

Tweet media one

1

1

3

@serinachang5

Serina Chang

4 years

@BenLangmead @nature @2plus2make5 @PangWeiKoh @jalinegerardin @beth_redbird @davidgrusky @jure The only time-varying behavior given to the model is mobility, so changes in mobility completely explain why restaurants & gyms contributed less to *predicted* infections over time. IRL though, I agree other types of behavior like mask-wearing affect infectiousness over time.

0

0

4

@serinachang5

Serina Chang

3 years

So well deserved! Huge congrats, @2plus2make5 !!

@2plus2make5

Emma Pierson

3 years

Honored to have been named to MIT @techreview 's 35 Innovators Under 35. Very grateful to the mentors and friends who collaborated on the work this award recognizes!!!

28

11

366

0

0

4

@serinachang5

Serina Chang

4 years

Thanks GPCE/Erin Raymond for the spotlight interview! We chatted about my recent work with @jugander on the social impact of rec systems, and more broadly about my research interests in complex systems of human behavior. Stay tuned for part 2! (we’ll be discussing COVID modeling)

@comp_epi

Computational Epidemiology

4 years

You will definitely want to watch this Student Spotlight - @serinachang5 is doing great things @Stanford

0

0

1

0

2

4

@serinachang5

Serina Chang

4 years

@estebanmoro @tiagopeixoto @tinaeliassi @mattk7 @leoferres @svscarpino @jkbren @SafeGraph @jure We also refrain from reporting results in the paper about specific census block groups / points of interest, and only report in groups (eg, CBG deciles, POI categories). And yes, the 98 mil refers to total population size of all CBGs that we model.

1

0

3

@serinachang5

Serina Chang

3 years

@2plus2make5 Yup same trend. Pretty even among whom I follow, but skewed male among my followers.

Tweet media one

1

0

3

@serinachang5

Serina Chang

2 years

@PangWeiKoh @uwcse @GoogleAI @_beenkim Congrats @PangWeiKoh !!!! UW is very lucky to have you. Excited to see what you do next :)

0

0

2

@serinachang5

Serina Chang

1 year

Spillovers introduce tradeoffs: while local policies provide flexibility between regions, their efficacy may be seriously undermined by spillovers. However, due to endogenous policymaking, there are few opportunities to reliably estimate causal spillovers or evaluate tradeoffs 2/

1

0

3

@serinachang5

Serina Chang

4 years

@avi_collis @mrfrank5790 Thank you!! We really enjoyed your paper in PNAS as well!

0

0

3

@serinachang5

Serina Chang

7 months

@yaledatascience @Stanford Thanks so much, I'll definitely take a look!

0

0

1

@serinachang5

Serina Chang

2 years

Thanks for shoutout, @manoelribeiro !! Really enjoyed your talk as well :)

@manoelribeiro

Manoel

2 years

@illegaldaydream @benjamindhorne @tizianopiccardi @sal_giorgi @Fra_Fabbri @serinachang5 & @jugander contrast a recommender model with an "organic search" counterfactual model. Although these models differ only in where the noise is, they lead to drastically different individual and collective outcomes. This was my fav paper 😅

Tweet media one

1

4

14

0

0

3

@serinachang5

Serina Chang

1 year

The key is that tier was assigned at the *cutoffs* of COVID metrics. We thus develop a regression discontinuity design-based framework to estimate how visits btwn counties change due to tiers. Do visits from county A to B increase when B is in a less restricted tier than A? 4/

1

0

3

@serinachang5

Serina Chang

7 months

@LevanCarrie @JaeJaeykim2 @Stanford Oh that looks interesting, thanks for the pointer!!

0

0

3

@serinachang5

Serina Chang

1 year

However, an intermediate strategy of macro-county restrictions—where we optimize county partitions by solving a minimum k-cut problem on a graph weighted by our spillovers—can recover over 90% of statewide reductions, while maintaining substantial flexibility between counties 7/

Tweet media one

1

0

3

@serinachang5

Serina Chang

2 years

To answer this question, we introduce two contrasting models: (1) a “recommender” model that captures a generic personalized recommender system, (2) an “organic” model where users search for items without the mediation of any system. 2/5

Tweet media one

1

0

3

@serinachang5

Serina Chang

3 years

@2plus2make5 Aww thanks Emma :) I couldn't have done it without you!

0

0

3

@serinachang5

Serina Chang

11 months

...however, for holdouts who eventually “converted” (showed vaccine intent), their concerns nearly reverse around conversion time, looking much more like early adopters than their typical selves – aside from a few important differences. 11/

Tweet media one

2

2

3

@serinachang5

Serina Chang

11 months

To fill these gaps, we employ anonymized search logs! We discover that they are amazingly powerful at detecting vaccine seeking, concerns, news exposure, etc, right from real-world clicks and queries. BUT how do we make sense of billions of unlabeled + unstructured searches? 3/

1

1

2

@serinachang5

Serina Chang

2 years

@officialKrishD @rohanalchemist @MSFTResearch @erichorvitz @adamfourney Thanks Rohan and Krish! Would love to chat -- let's coordinate over email!

1

0

2

@serinachang5

Serina Chang

7 months

@CesarAUribe @Stanford @RiceEngineering Awesome thanks, will take a look!

0

0

1

@serinachang5

Serina Chang

2 years

@msaveski @UW_iSchool @UW Congrats Martin!! @UW is lucky to have you!

0

0

2

@serinachang5

Serina Chang

7 months

@lilyxu0 Aw thank you @lilyxu0 !! I really appreciate it. Your research is such an inspiration to me too!

0

0

2

@serinachang5

Serina Chang

3 years

Despite never having worked together in person, Pang Wei has helped me become a better researcher, coder, writer, and thinker. I feel so lucky to be able to call him a mentor, collaborator, and friend. 😍

0

0

2

@serinachang5

Serina Chang

11 months

Our solution: graph machine learning. First, we impose structure by representing search logs as a *query-click graph*, then we develop methods to detect user intents and categorize user interests using graph ML + human annotation. 4/

Tweet media one

1

1

2

@serinachang5

Serina Chang

3 years

4/ To build this tool, we’ve updated our model substantially — adding + validating new features (like mask-wearing), fitting to smaller metro areas and new time periods, improving our computational infrastructure so that we can run millions of model realizations efficiently.

Tweet media one

1

0

2

@serinachang5

Serina Chang

3 years

@PangWeiKoh Thank you Pang Wei!!! So glad we got to do this project together, and, as always, I had so much fun and learned so much from working with you! 😍

0

0

2

@serinachang5

Serina Chang

7 months

@mantaflight @ben_golub @Stanford I'm broadly interested in TT faculty positions related to my research! Including CS, IS, data science, business schools, etc

1

0

2

@serinachang5

Serina Chang

11 months

@Albertyusun @erichorvitz @adamfourney @MSFTResearch Thanks Albert!! :)

0

0

1

@serinachang5

Serina Chang

11 months

Wait, but is Bing representative? Well, coverage isn’t uniform across the US, so we carefully estimate Bing coverage per ZIP and correct for this. See M3 for details: we also decompose sources of bias, evaluate bias from our classifier, and compare Bing + Google trends 12/

1

0

2

@serinachang5

Serina Chang

11 months

Concerns of early adopters vs holdouts differ significantly even within categories: eg, in Vaccine Safety, early adopters are more interested in normal side effects, severe side effects (eg, blood clots); holdouts far more interested in vaccine myths, exemptions, FDA approval 10/

1

1

2

@serinachang5

Serina Chang

3 years

3/ Our tool allows policymakers to explore the impact of fine-grained changes in mobility on predicted infections: eg, what if restaurants were returned to 50% of their pre-pandemic levels of mobility, essential retail to 100%, and other categories retained their current levels?

Tweet media one

1

0

2

@serinachang5

Serina Chang

3 years

Thank you for writing this, Emma! I couldn’t agree more. To add on, I’m so grateful to @PangWeiKoh for not only his essential contributions to our methods, but also for going above + beyond by joining Emma in becoming the best mentors I could ask for — on this project and in life

@2plus2make5

Emma Pierson

3 years

He's never even given a talk about it, but his fingerprints are all over this work - in the decades-old optimal transport algorithms applied to a totally novel setting; in the integrals correcting the visit counts; in the winsorization of input data to defend against outliers. 7/

1

1

13

1

0

2

@serinachang5

Serina Chang

3 years

5/ There are limitations to our tool, eg, modeling assumptions, mobility data doesn't cover all populations. Also, we focus on the effects of mobility on transmission, but other work is needed on how policymakers can reach target levels of mobility (we're looking into this now!)

1

0

1

@serinachang5

Serina Chang

1 year

@_arodriguezca @RealAAAI Likewise!! Really enjoyed learning about your work and chatting about our shared interests :)

0

0

1

@serinachang5

Serina Chang

9 months

Please stop by if you want to chat or message me to meet! I'll be there Aug 7 and morning of Aug 8 :)

0

0

1

@serinachang5

Serina Chang

7 months

@ccanonne_ @Sydney_Uni @jose That’s great to hear, thanks for the pointer! And yes, I see a great fit between Complex Systems and my research

1

0

1

@serinachang5

Serina Chang

7 months

@roshni714 Thank you Roshni!!! 🙏🏼 so glad we’ve gotten to chat more recently!

0

0

1

@serinachang5

Serina Chang

2 years

@AniseSmith @hood_medicine Thank you so much!!

0

0

1

@serinachang5

Serina Chang

7 months

@emilio__ferrara @Stanford @CSatUSC Thanks! Yes I’m definitely interested in USC and impressed by its focus on AI and Society, like CAIS!

1

0

1

@serinachang5

Serina Chang

7 months

@DrDesmondPatton Thank you @DrDesmondPatton !!! It's so great to hear from you - I hope you're doing well!

0

0

1

@serinachang5

Serina Chang

11 months

We develop a “vaccine intent classifier” that detects when a user is trying to get the COVID vaccine on search. What’s unique is that our classifier not only detects queries, eg, [covid vaccine near me], but also URL clicks, eg, on the CVS COVID vaccine registration page. 5/

1

1

1