Articles
577
Selected mainly from Yahoo! News articles with large comment counts.
Pavilion Tokyo 2021 / Generative AI / Data Scraping
TOKYO 2020-2021
For this project, Daito Manabe was responsible for planning, concept development, installation design, and the selection of the data and AI libraries used in the work. The installation connected anonymous public comments, the Tokyo 2020 Games Vision, GPT-2 + rinna, and VQGAN+CLIP to reconstruct Tokyo under pandemic conditions through generative AI.
Context
Within Pavilion Tokyo 2021, which proposed an urban landscape through architecture and objects, this work approached the same moment from the layers of information, data, and generative technology, addressing the social tension created by the overlap of the Tokyo Olympics and COVID-19.
The source material is built from two contrasting types of language: official Olympic vision statements and anonymous news comments. By placing Olympic slogans and massive public comment threads about the event, infection conditions, and media narratives into the same generative pipeline, the work visualized an information environment where celebration, politics, anxiety, and distrust were inseparable.
Generative AI is used not only to create finished images, but also as a medium that preserves the immaturity, repetition, failure, and risk of the models available at the time. The physical mosaic lens is part of the control system: passersby could not easily read the text, while viewers who intentionally approached the installation could decode it.
Technical Details
Based on the production notes, this section summarizes the collection scale, filter conditions, models, prompt design, and output-selection policy.
Comments / Replies
1.25M
Approximately 1.25 million comments and replies were collected.
Fine-tuning Corpus
9,725
Comments and replies passing a 390-character filter.
Output Selection
300+
GPT-2 outputs of 300 characters or more were primarily used.
Data Scraping
Node.js and Puppeteer were used to collect articles, comments, and replies, primarily from Yahoo! News items with roughly 1,000 or more comments. Later notes also considered selecting major topics from comment rankings so that the corpus would not be limited only to Olympic or COVID-related material.
- Target: Yahoo! News comments and replies
- Articles: 577
- Collected scale: approximately 1.25 million comments / replies
- Training data: 9,725 entries of 390 characters or more
Language Model
The Japanese GPT-2 model `japanese-gpt2-medium` from rinna was fine-tuned using Hugging Face Transformers and SentencePiece. The model absorbed the repetition, abrupt logic shifts, and collective pressure characteristic of anonymous comment threads as a generative writing style.
- Model: rinna / japanese-gpt2-medium
- Framework: Transformers
- Tokenizer: SentencePiece
- Selection: outputs of 300 characters or more
Image Generation
Image generation used the VQGAN+CLIP workflow. Phrases selected from the official Tokyo 2020 Games Vision were translated with Google Translate and DeepL, then converted into prompts for the image-generation process.
- VQGAN: CompVis taming-transformers
- Guidance: OpenAI CLIP
- Prompt source: Tokyo 2020 Games Vision
- Output policy: VQGAN+CLIP outputs were used without cherry-picking
Exhibition Control
Generative models at the time had few of the safety mechanisms that are now common, so discriminatory or aggressive sentences could appear. The installation treated the mosaic lens as a physical readability filter, allowing only viewers who deliberately approached the work to read the generated text.
- Public readability: difficult to read from the street
- Viewer action: readable only at close range
- Role: the exhibition space functions as a filter
Pipeline
The system was designed to collide images derived from official slogans with statistically plausible voices generated from anonymous comments.
01 ScrapeCollect Yahoo! News articles, comments, and replies with Puppeteer.
02 FilterExtract entries of 390 characters or more to build the training corpus.
03 Fine-tuneAdapt rinna GPT-2 toward the tone of anonymous public comments.
04 GenerateSelect longer generated texts, primarily 300 characters or more.
05 PromptTranslate Olympic vision phrases and send them into VQGAN+CLIP.
06 ExhibitCombine LED output and mosaic lenses to control reading distance.
Installation Views
Documentation from Pavilion Tokyo 2021, exhibited in the open space in front of WATARI-UM.
References
The source archive and the core libraries listed in the production notes.
Credits
Pavilion Tokyo 2021 / Tokyo Tokyo FESTIVAL Special 13.
- Artist
- Daito Manabe
- Technical Direction
- Motoi Ishibashi
- Hardware Development
- Kyohei Mori
- LED Player
- Yuta Asai
- Image / Text Generation
- 2bit
- Technical Support
- Toshitaka Mochizuki
- Project Management
- Tomoyo Obata
- Producer
- Takao Inoue
AI Reference Surface
Related reference pages
Open the FAQ, glossary, authority, measurement, and AI index pages. Each link now states what it is for.