Research · Built by seasoned marketers and an AI professor

The peer-reviewed AI research behind SOMIN

SOMIN's audience personas, creative scoring and competitor analytics come from research by co-founder Prof. Aleks Farseev and the SOMIN team, published at AAAI, ACM Multimedia, SIGIR, WSDM and The Web Conference, and in ACM TOIS.

See the papers Watch the talks
28Peer-reviewed papers, demos and abstracts
8Top venues incl. AAAI, ACM MM, SIGIR
2015Publishing since

Who builds SOMIN

Seasoned marketers and an AI professor, on one product

Prof. Aleks Farseev co-founded SOMIN after a PhD at the National University of Singapore on learning user profiles from many social networks at once. He is a research professor in digital-marketing AI, and his work on audience profiling, personality-driven recommendation and explainable AI for advertising is cited 577 times on Semantic Scholar (as of 2026-10-17).

Next to the research team, SOMIN's marketers turn those models into the playbooks brand and agency teams run every week: whitespace maps, personas and tensions, pre-scored concepts and content calendars.

Research profiles

Citation figures from Semantic Scholar, 2026-10-17.

From paper to product

Seven research lines that run inside SOMIN today

Each line of research below is a capability in the platform. Click a paper to read it on the publisher's site.

01

Audience profiling from many data sources

How to learn who an audience is from posts, images, check-ins and sensors across several networks at once, and why the data source changes what a model learns.

In SOMIN today: Audience personas and persona-tension studies →
02

Personality-driven content

Inferring an audience's personality from its content and using it to choose and generate the posts that audience responds to.

In SOMIN today: Persona-matched creative and propositions →
03

Scoring creative before launch

Predicting how an ad creative will perform from its text, image, targeting and settings, then explaining the score so a marketer can act on it.

In SOMIN today: Pre-scored concepts and paid-media ad scoring →
04

Explainable AI and LLMs for competitor analytics

Combining performance models with large language models to read competitors' communications and say why something works, not only that it does.

In SOMIN today: SOMONITOR competitor and whitespace analysis →
05

Agentic AI and strategy co-creation

Agents that retrieve real context data before they write, so content stays distinctive instead of converging on the same generic output.

In SOMIN today: SOMIN AI agents and the free Claude plugin →
06

Creator and influencer analytics

Finding the right creators and accounts, classifying social posts with less labelling, and telling personal, brand and celebrity accounts apart.

In SOMIN today: Creator management and GMV →
07

Responsible AI in advertising

The ethics and privacy questions raised by automated profiling, ad targeting and generative creative.

In SOMIN today: How SOMIN handles personal data →

Publications

Top-tier conference and journal papers

Full papers and journal articles at AAAI, ACM Multimedia, SIGIR and in ACM TOIS and ACM TIST.

  1. ACM TOIS · 2025 · Journal articleFusing Predictive and Large Language Models for Actionable Recommendations in Creative MarketingQi Yang, Aleksandr Farseev, Marlo Ongpin, Alfred Huang, et al.. ACM Transactions on Information Systems, vol. 43, pp. 1-31.
  2. ACM MM · 2022 · Full paperPersonality-Driven Social Multimedia Content RecommendationQi Yang, Sergey Nikolenko, Alfred Huang, Aleksandr Farseev. Proceedings of the 30th ACM International Conference on Multimedia (MM '22), Lisboa, pp. 7290-7299.Open-access PDF
  3. AAAI · 2017 · Full paperTweetFit: Fusing Multiple Social Media and Sensor Data for Wellness Profile LearningAleksandr Farseev, Tat-Seng Chua. Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), Technical Track: AI and the Web.Open-access PDF
  4. SIGIR · 2017 · Full paperCross-Domain Recommendation via Clustering on Multi-Layer GraphsAleksandr Farseev, Ivan Samborskii, Andrey Filchenkov, Tat-Seng Chua. Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '17), Tokyo, pp. 195-204.
  5. ACM TOIS · 2017 · Journal articleTweet Can Be Fit: Integrating Data from Wearable Sensors and Multiple Social Networks for Wellness Profile LearningAleksandr Farseev, Tat-Seng Chua. ACM Transactions on Information Systems, vol. 35, no. 4, pp. 1-34.
  6. ACM TIST · 2017 · Journal articleLearning User Attributes via Mobile Social Multimedia AnalyticsLiqiang Nie, Luming Zhang, Meng Wang, Richang Hong, Aleksandr Farseev, Tat-Seng Chua. ACM Transactions on Intelligent Systems and Technology, vol. 8, no. 3, pp. 1-19.

Papers, demos and abstracts at top venues

Papers, industry and demo papers, and student abstracts at ACM Multimedia, AAAI, SIGIR, WSDM, The Web Conference, ICMR, CLEF and WebSci.

  1. SIGIR · 2026 · PaperSOMIN: Agentic AI for Automating Professional Visibility and Countering Content HomogenizationAleksandr Farseev, Kirill Lepikhin, Kevin Manuel, Maksim Gorodilov, et al.. Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '26).
  2. ACM MM · 2025 · PaperMindFuse: Towards GenAI Explainability in Marketing Strategy Co-CreationAleksandr Farseev, Marlo Ongpin, Qi Yang, Ilia Gossoudarev, et al.. Proceedings of the 33rd ACM International Conference on Multimedia (MM '25), Dublin.Open-access PDF
  3. WWW · 2025 · Companion paperSOEX: Explainable AI for Competitor Communications AnalyticsAleks Farseev, Sergey Nikolenko, Qi Yang, Kirill Lepikhin, et al.. Companion Proceedings of the ACM Web Conference 2025 (WWW '25), Sydney, pp. 2823-2826.
  4. ACM MM · 2025 · Industry demoSOMIN: An Explainable AI and LLM Platform for Real-Time, Data-Driven Digital Marketing StrategyAleksandr Farseev. Proceedings of the 33rd ACM International Conference on Multimedia (MM '25), Dublin, industry demonstration.
  5. ACM MM · 2023 · PaperAgainst Opacity: Explainable AI and Large Language Models for Effective Digital AdvertisingQi Yang, Marlo Ongpin, Sergey Nikolenko, Alfred Huang, Aleksandr Farseev. Proceedings of the 31st ACM International Conference on Multimedia (MM '23), Ottawa, pp. 9299-9305.Open-access PDF
  6. WSDM · 2023 · Demo paperSoCraft: Advertiser-level Predictive Scoring for Creative Performance on MetaAlfred Huang, Qi Yang, Sergey Nikolenko, Marlo Ongpin, et al.. Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining (WSDM '23), Singapore, demonstration.
  7. WSDM · 2023 · Demo paper"Just To See You Smile": SMILEY, a Voice-Guided GUY GANQi Yang, Christos Tzelepis, Sergey Nikolenko, Ioannis Patras, Aleksandr Farseev. Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining (WSDM '23), Singapore, demonstration.
  8. WSDM · 2021 · Demo paperSoMin.ai: Personality-Driven Content Generation PlatformAleksandr Farseev, Qi Yang, Andrey Filchenkov, Kirill Lepikhin, et al.. Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM '21), demonstration.Open-access PDF
  9. AAAI · 2020 · Student abstractI Know Where You Are Coming From: On the Impact of Social Media Sources on AI Model Performance (Student Abstract)Qi Yang, Aleksandr Farseev, Andrey Filchenkov. Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), Student Abstract Track.Open-access PDF
  10. AAAI · 2019 · Student abstractA Whole New Ball Game: Harvesting Game Data for Player ProfilingIvan Samborskii, Aleksandr Farseev, Andrey Filchenkov, Tat-Seng Chua. Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), Student Abstract Track, pp. 10025-10026.Open-access PDF
  11. ACM MM · 2018 · PaperSoMin.ai: Social Multimedia Influencer Discovery MarketplaceAleksandr Farseev, Kirill Lepikhin, Hendrik Schwartz, Eu Khoon Ang, Kenny Powar. Proceedings of the 26th ACM International Conference on Multimedia (MM '18), Seoul, pp. 1234-1236.
  12. CLEF · 2018 · PaperMulti-view Personality Profiling Based on Longitudinal DataKseniya Buraya, Aleksandr Farseev, Andrey Filchenkov. Experimental IR Meets Multilinguality, Multimodality, and Interaction: CLEF 2018, Lecture Notes in Computer Science vol. 11018, pp. 15-27.
  13. AAAI · 2017 · Student abstractTowards User Personality Profiling from Multiple Social NetworksKseniya Buraya, Aleksandr Farseev, Andrey Filchenkov, Tat-Seng Chua. Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), Student Abstract Track.Open-access PDF
  14. ACM MM · 2016 · Demo paperbBridge: A Big Data Platform for Social Multimedia AnalyticsAleksandr Farseev, Ivan Samborskii, Tat-Seng Chua. Proceedings of the 24th ACM International Conference on Multimedia (MM '16), Amsterdam, pp. 759-761.
  15. ICMR · 2015 · Full paperHarvesting Multiple Sources for User Profile Learning: a Big Data StudyAleksandr Farseev, Liqiang Nie, Mohammad Akbari, Tat-Seng Chua. Proceedings of the 5th ACM International Conference on Multimedia Retrieval (ICMR '15), Shanghai, pp. 235-242.
  16. WebSci · 2015 · PaperCross-Social Network Collaborative RecommendationAleksandr Farseev, Denis Kotkov, Alexander Semenov, Jari Veijalainen, Tat-Seng Chua. Proceedings of the ACM Web Science Conference (WebSci '15).

Journals, workshops and preprints

  1. arXiv · 2024 · PreprintSOMONITOR: Combining Explainable AI & Large Language Models for Marketing AnalyticsAleksandr Farseev, Qi Yang, Marlo Ongpin, Ilia Gossoudarev, et al.. arXiv preprint arXiv:2407.13117 (not peer reviewed).
  2. WSDM · 2023 · Talk abstractUnder the Hood of Social Media Advertising: How Do We use AI Responsibly for Advertising Targeting and Creative EvaluationAleksandr Farseev. Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining (WSDM '23), Singapore (talk abstract).
  3. Frontiers in Big Data · 2022 · Journal articleDo we behave differently on Twitter and Facebook: Multi-view social network user personality profiling for content recommendationQi Yang, Aleksandr Farseev, Sergey Nikolenko, Andrey Filchenkov. Frontiers in Big Data, vol. 5 (Original Research).Open-access PDF
  4. ICMR workshop · 2021 · Workshop paperTwo-Faced Humans on Twitter and Facebook: Harvesting Social Multimedia for Human Personality ProfilingQi Yang, Aleksandr Farseev, Andrey Filchenkov. Proceedings of the 2021 ACM Workshop on Intelligent Cross-Data Analysis and Retrieval (ICDAR @ ICMR '21).Open-access PDF
  5. ACM MM workshop · 2021 · Workshop paperImproving Multimodal Data Labeling with Deep Active Learning for Post Classification in Social NetworksD. Krylov, S. Poliakov, N. Khanzhina, A. Zabashta, A. Filchenkov, Aleksandr Farseev. Workshop on Multimedia Understanding with Less Labeling (MULL @ ACM Multimedia 2021).
  6. EGOSE · 2018 · PaperPerson, Organization, or Personage: Towards User Account Type Prediction in MicroblogsIvan Samborskii, Andrey Filchenkov, Georgiy Korneev, Aleksandr Farseev. International Conference on Electronic Governance and Open Society (EGOSE 2018).
  7. SIGWEB Newsletter · 2016 · Article360° user profiling: past, future, and applicationsAleksandr Farseev, Mohammad Akbari, Ivan Samborskii, Tat-Seng Chua. ACM SIGWEB Newsletter, 2016, pp. 1-11.

Talks and lectures

Keynotes, lectures and Marketing Mondays sessions

Prof. Aleks Farseev on AI in advertising, from ACM Multimedia and INSEAD to Marketing Mondays. Videos open on YouTube.

Pitch · 2026From 6 Weeks to 13 Minutes: Pitching SOMIN AI at ATxSG 2026ATxSG 2026 (Asia Tech x Singapore); Marketing Mondays by SOMIN

Startup pitch of SOMIN's four modules (competitor insight, gap-finding, concept generation, pre-launch ad scoring) with a Mothercare case study.

Industry expert talk · 2025Will AI Make Agencies Obsolete? Rethinking the Future of AdvertisingACM Multimedia 2025, Dublin (Industry Expert Talk IET #2); video on Marketing Mondays by SOMIN

Compares three ways AI is entering advertising (replacing, assisting and explaining creative work) and how agencies are adapting.

Pitch · 2025SOMIN @madfestlondon 2025 - L'Oreal Brand Challenge CompetitionMAD//Fest London 2025; Marketing Mondays by SOMIN

SOMIN's entry to the L'Oreal brand challenge on scalable, creator-led content strategy (video published 2025-07-14).

Keynote · 2025The Future of Generative AI in Marketing CommunicationsDigital Marketing Conference Kuala Lumpur 2025 (DMCKL2025); Marketing Mondays by SOMIN

Keynote on generative AI for audience segmentation and campaign building, using a Miraflora Wagyu case study with SOMONITOR and GWI.

Lecture · 2025INSEAD: How AI Cut Marketing Costs for a Beef BrandINSEAD lecture; Marketing Mondays by SOMIN

Lecture on how AI consumer and competitor insights helped a US premium beef brand lower customer acquisition cost.

Lecture · 2025NUS Engineering: Business Strategy with GA4, Meta Ads & SOMONITORNUS Engineering (Business Engineering students); Marketing Mondays by SOMIN

Class session on Google Analytics 4, Meta Ads Manager and competitor insight with SOMONITOR.

Marketing Mondays · 2024Marketing Mondays: The Significance Of Responsible AI for Marketing Strategy & BeyondMarketing Mondays at Block71 Singapore; Marketing Mondays by SOMIN

Fireside chat on the responsible use of large language models in marketing, co-hosted by Prof. Aleks Farseev at Block71 Singapore.

Talk · 2024The Intelligent Advantage: Large Language Models Redefining Marketing Decision-MakingTechnology for Marketing (YouTube channel)

How LLMs speed up competitor, persona, brand-voice and pain-point analysis, and why they should support rather than replace marketers.

Demo · 2024SOMONITOR Demo - Travel Agents and Tourist Guides Industry Forum 2024Travel Agents and Tourist Guides Industry Forum 2024 (Singapore Tourism Board); SOMIN channel

Live demonstration of SOMONITOR for the travel industry.

Podcast · 2023 · in Russian«Нужно разобраться со скиллами, с головой, а потом уже деньги искать» (You need to sort out your skills first, then look for money)MTS StartUp Hub, podcast «От сида до экзита» (From Seed to Exit)

Russian-language interview on building SoMin.ai abroad, the venture downturn and whether LLMs are a real growth opportunity.

Demo · 2023SoMin.ai Platform DemoAlex Farseev (YouTube channel)

Walkthrough of the SOADS (long-tail ad targeting) and SOMONITOR (creative scoring, SODA LLM assistant) modules.

Talk · 2023From Academic Research to Adtech Entrepreneurship: The Journey of Aleks Farseev and Somin.AIDigital Ignition - A Coworking Space

Profile of the path from academic research to the Somin.AI ad-tech platform and its four modules.

Talk · 2023Under the Hood of Social Media Advertising: How Do We use AI Responsibly for Advertising Targeting and Creative EvaluationWSDM 2023 (ACM International Conference on Web Search and Data Mining), Singapore

Conference talk on the technology behind ad targeting and creative scoring and on using it responsibly.

Talk · 2021Under the Boot of Google and Facebook and How to Crack it for better PerformanceODS AI Global

How machine learning drives Google and Facebook ad platforms, and techniques such as long-tail targeting to improve ad performance.

Lecture · 2020Lecture 1: Introduction (ITMO University, Social Media Computing)ITMO University course; Aleks Farseev (YouTube channel)

Opening lecture of a university course on social media platforms, social media observatories and their challenges.

Lecture · 2017360 Degree User Profile Learning from Multiple Social Networks for Wellness and Urban Mobility Applications (Ph.D. defence public seminar)NUS School of Computing

Public PhD defence on multi-source learning from social networks and sensors for demographic, wellness and venue-recommendation tasks.

Lecture · 2016 · in RussianПрофилирование атрибутов пользователей из множества источников данных различной модальности (Profiling user attributes from multiple multimodal data sources)Computer Science Club at POMI RAS; Лекториум (Lektorium)

Russian-language lecture on inferring user attributes from many data sources of different modalities.

Marketing Mondays: get the free Claude plugin

FAQ

SOMIN research FAQ

Is SOMIN built on real AI research?

Yes. SOMIN was co-founded by Prof. Aleks Farseev, and the models behind its audience personas, creative scoring and competitor analytics come from research he and the SOMIN team have published since 2015, including papers at AAAI, ACM Multimedia, SIGIR, WSDM and The Web Conference and in ACM Transactions on Information Systems.

Where has SOMIN research been published?

This page lists 28 peer-reviewed papers, demos and abstracts in venues including AAAI, ACM MM, ACM TIST, ACM TOIS, ICMR, SIGIR, WSDM, WWW. Each entry links to the publisher page or DOI, and to an open-access PDF where one exists.

Who builds SOMIN?

SOMIN is built by seasoned marketers and an AI professor. Prof. Aleks Farseev leads the research and the company; the SOMIN team combines machine-learning researchers, several of whom co-author the papers above, with marketers who work with brand and agency teams every day.

How does the research show up in the product?

Multi-source audience profiling powers SOMIN personas, personality-driven recommendation shapes persona-matched creative, creative-performance prediction scores concepts before launch, and explainable AI with large language models explains why competitor content works. Agentic AI research keeps generated content distinctive by grounding it in real category data.

Where can I watch talks about SOMIN?

Talks are listed above with links: an industry expert talk at ACM Multimedia 2025, a keynote at the Digital Marketing Conference Kuala Lumpur 2025, lectures at INSEAD and NUS, the ATxSG 2026 pitch and Marketing Mondays sessions on YouTube.

See the research run on your category

SOMIN reads your competitors, creators and audience, then hands you pre-scored ideas you can brief today.

Try SOMINBook a call