IR_oldie Profile Banner
Mark Sanderson Profile
Mark Sanderson

@IR_oldie

Followers
4K
Following
2K
Media
312
Statuses
3K

I'm a search engine researcher. I tweet about information retrieval (IR) and uni work. I'm at RMIT University, these are my personal opinions.

Melbourne
Joined March 2010
Don't wanna be here? Send us removal request.
@IR_oldie
Mark Sanderson
2 months
I enjoyed the paper because it highlighted how much people use search for "do it yourself" fact checking. This is a topic IR researchers don't examine enough.
0
0
4
@IR_oldie
Mark Sanderson
2 months
Searching also caused people to trust more true news from low quality news sources.
1
0
2
@IR_oldie
Mark Sanderson
2 months
The way people searched seemed to impact the likelihood that they mistook fake news for true news.
1
0
1
@IR_oldie
Mark Sanderson
2 months
I suspect one of the reasons why so many people were included in the crowd sourcing studies was to bump up the power of the study.
1
0
0
@IR_oldie
Mark Sanderson
2 months
The authors run five extensive crowd sourcing studies collectively drawing on the responces of >14K people. Each study examined the question from different angles. Each found searching can make people more likely to believe false information. However, the effect is small.
1
0
0
@IR_oldie
Mark Sanderson
2 months
We had fun discussing this @Nature 2024 paper "Online searches to evaluate misinformation can increase its perceived veracity". Can searching make people think false information is true? The paper shows it can, a bit. Read on...
3
0
6
@IR_oldie
Mark Sanderson
4 months
My congratulations to my @RMIT colleague @danulaera and Kacper Sokol for being a recipient for their work on "Addressing Misunderstanding of AI Explanations Through Follow-up Interactions and Multi-modal Explainers".
@GoogleResearch
Google Research
4 months
We’re announcing the 87 professors selected for the 2025 Google Research Scholar Program — join us in congratulating these exceptional recipients and learn more about their groundbreaking work at https://t.co/sIoedpv9pI. #GoogleResearch #GoogleResearchScholar
1
1
5
@IR_oldie
Mark Sanderson
5 months
On the #SIGIR2025 list of accepted papers, the word "LLM" appears more frequently than the word "the". I may need to revise my stopword list :) https://t.co/1xKB4Zq5PI @ACMSIGIR
1
4
32
@IR_oldie
Mark Sanderson
5 months
"From Foundations to GPT in Text Classification: A Comprehensive Survey on Current Approaches and Future Trends", the latest review article from FnTIR
1
0
8
@IR_oldie
Mark Sanderson
5 months
If you were a fan of @BlinovaValeriia's 2023 WikiHowQA ACL paper https://t.co/amzo1htYIV, you might be interested to hear that the dataset from that work is now available for open download.
Tweet card summary image
huggingface.co
0
1
3
@IR_oldie
Mark Sanderson
5 months
Congratulations Dr. @NegarEmpr !
@NegarEmpr
Negar Arabzadeh
5 months
🎓 I successfully defended my PhD thesis today! Endless thanks to @claclarke for trusting in me and being the best supervisor I could ask for. Grateful to my committee and heartfelt thanks to all my collaborators over the past 4 years — I couldn’t have done it without you!
1
0
8
@IR_oldie
Mark Sanderson
5 months
Many congratulations to my fellow SIGIR Academicians who were inducted into the ACM SIGIR Class of 2025: David Carmel, Evgeniy Gabrilovich, Don Metzler, Chirag Shah, Ian Soboroff, and Min Zhang. All incredible contributors to IR.
0
1
22
@JeffDean
Jeff Dean
6 months
Someone just reminded me of this lecture I gave in 2009 that described the evolution of Google Search from 1999 to 2009. People who are interested in how our search systems work might find this interesting. It touches on disk-based serving systems, in-memory indices,
Tweet card summary image
videolectures.net
Building and operating large-scale information retrieval systems used by hundreds of millions of people around the world provides a number of interesting challenges. Designing such systems requires...
39
260
2K
@IR_oldie
Mark Sanderson
6 months
"Understanding and Mitigating Gender Bias in Information Retrieval Systems" By Shirin Seyedsalehi, Amin Bigdeli, Negar Arabzadeh, Batool AlMousawi, Zack Marshall, Morteza Zihayat and Ebrahim Bagheri https://t.co/9vPfbnyWIg
0
1
2
@IR_oldie
Mark Sanderson
6 months
Two more FnTIR articles are out: "Search as Learning", by Kelsey Urgo and Jaime Arguello
1
0
10
@IR_oldie
Mark Sanderson
6 months
RAG - why use "retrieval" in the acronym and not "search"? Then again would we be as excited about doing SAG?
4
0
13
@jobergum
Jo Kristian Bergum
7 months
Yup, current search infrastructure assumes human users, optimizing for short keyword queries and millisecond response times. AI agents have fundamentally different retrieval patterns. My thoughts on this shift in a thread 1/
@lennypruss
Lenny Pruss
7 months
The implications are profound. We need to build infrastructures that are agent-first rather than human-first. This requires reimagining the entire software development lifecycle (big blog post on this forthcoming).
3
34
383
@ACM_CHIIR
ACM CHIIR 2026
7 months
🎉 CHIIR 2025 has officially concluded. Huge thanks to organising teams, keynote speakers, presenters, volunteers, and everyone who joined us — see you next year in Seattle, @chirag_shah @ryen_white ! 👋 @GeorgeRBuchanan @HaimingLiu1 @DanaChatter @IR_oldie @JTrippas @damiano10
0
6
12
@IR_oldie
Mark Sanderson
7 months
Got a chance to look at this excellent review paper, a fine piece of work!
@krisztianbalog
Krisztian Balog
10 months
Check out our new paper w/ ChengXiang Zhai, in which we explore the role user simulation plays in the era of Generative AI, from modeling user behaviour to generating synthetic data to evaluating AI systems: https://t.co/qZDwZuIajL #UserSimulation #AI #GenerativeAI #AGI
0
0
10