Call for Papers 13th International Conference on CMC and Social Media Corpora for the Humanities (CMC-Corpora 2026) Date: 27–28 August 2026 Location: University of Oulu, Finland Website: https://cmc2026.orghttps://cmc2026.org/ Recent advances in social media and communication technologies are expanding the scope of computer-mediated communication (CMC) research. New platforms and formats, from short video apps like TikTok to community platforms like Discord, are generating massive volumes of user-generated content and multimodal interactions. Due to their unprecedented popularity, “the question of how meaning is produced in these videos is becoming increasingly important… However, systematic approaches to the analysis of these meanings are still scarce” (Grzenkowicz & Wildfeuer, 2025, p. 1143). At the same time, AI techniques are opening novel avenues for analysis of digital discourse. Social media provides “a massive repository of real-time data” that demands “advanced tools capable of understanding complex language, context, and framing”, and “LLMs offer potential in this domain, with their ability to process large amounts of text and extract meaningful insights” (Nguyen et al., 2025, p. 1331). We adhere to a broad definition of CMC and social media, encompassing a wide range of digital communication media – including email, forums, chats and messenger apps (e.g. WhatsApp, Discord), social networks (Facebook, 𝕏/Twitter, Instagram), short-video and streaming platforms (TikTok, YouTube), online gaming and virtual worlds, and other emerging channels. Submission Types Short Papers (Oral Presentations): 3–5 pages, anonymized short papers for researchers who wish to give a talk. These submissions should follow the conference template and report completed or well-advanced research. Authors of accepted short papers will be allotted a 30-minute slot (20 minutes for presentation + 10 minutes Q&A) to present their work. All accepted short papers will be published in the conference proceedings. Abstracts (Poster Presentations): up to 300 words (excluding references), anonymized abstracts for work-in-progress, early-stage research, software or corpus demonstrations to be presented as posters. Authors of accepted abstracts will present their work during the poster session at the conference, allowing one-on-one discussion and feedback. Review & Presentation All submissions will undergo a double-blind peer review by at least two members of the scientific committee. Each submission will be evaluated for relevance to the conference's themes, methodological soundness, and contribution to the field. Based on the reviews, submissions may be accepted for oral talk or poster presentation as appropriate. Authors of accepted short papers will give oral presentations in themed panels (each talk 20 minutes followed by 10 minutes of discussion). Authors of accepted poster abstracts will present their work during a dedicated poster and demo session, where interactive discussion is encouraged. At the start of the conference, all accepted short papers will be made available in online proceedings. After the conference, authors of select top papers may be invited to submit extended versions for publication in a special issue or edited volume, showcasing significant advances in CMC and social media corpus research. Topics of Interest We invite submissions on CMC and social media, including but not limited to the following topics of interest: Development of CMC Corpora / Social Media Corpora

* Building and curating CMC corpora: from data collection (APIs, web scraping) to publication and sharing * Open access data for CMC research: addressing ethical challenges and GDPR compliance in data sharing * Annotating CMC data: frameworks for labeling genres, linguistic features, metadata (including novel phenomena like emojis, memes) * Multimodal and multimedia corpora: handling texts, images, audio, video (e.g. short video content) in unified corpora * Big data and streaming corpora: managing large-scale social media datasets, real-time data collection, and data sampling strategies * Legal issues in social media data: copyright, terms-of-service limitations, and long-term archiving of corpora from platforms (including new platforms like TikTok or Discord)

Analysis of CMC Corpora / Social Media Communication

* Sociolinguistic studies of online communication (language variation, stylistic adaptation, community norms in CMC) * Discourse analysis of digital interactions (conversation structures, politeness, argumentation in forums, comment threads, group chats, etc.) * Linguistic characteristics of CMC (slang, abbreviations, emojis, code-switching, vernaculars across different platforms) * Multimodal communication in social media (integration of text with visuals, videos, GIFs; meaning-making through memes, hashtags, and trends) * Multilingualism and code-switching in online contexts (cross-lingual communication, translation in user-generated content) * CMC in language education and digital literacy (use of social media corpora for language learning, teaching communication skills online) * Platform-specific communication practices (e.g. discourse patterns unique to TikTok, Instagram stories, or Discord communities, and how they evolve)

Computational Processing (NLP) of CMC / Social Media Data

* Text normalization for noisy CMC data (handling misspellings, abbreviations, emoji to text, spoken-to-written style) * Part-of-speech tagging and lemmatization for social media text (adapting NLP tools to non-standard grammar and orthography) * Anonymization and pseudonymization techniques (protecting user privacy in corpora while preserving analytical value) * Syntactic parsing and semantic analysis of informal or ungrammatical CMC text (challenges for parser models on tweets, chats, etc.) * Transformer and LLM-based approaches for CMC analysis (applying large language models to classify content, summarize discussions, or generate synthetic data for under-resourced CMC domains) * Detection of harmful content and misinformation (e.g. hate speech identification, toxicity filtering, fact-checking and misinformation detection in social media corpora using AI/NLP methods) * Multimodal NLP techniques for social media (e.g. analyzing text in conjunction with images or videos, OCR on memes, speech-to-text in voice chats)

Important Dates (EEST where specified)

* Deadline paper/abstract submission: 15 April 2026, 23:59 EEST * Notification of acceptance: 1 June 2026 * Deadline revised paper/abstract submission: 15 July 2026, 23:59 EEST * Deadline registration for participation: 1 August 2026 * Conference: Thursday 27 – Friday 28 August 2026

Templates & Submission Guidelines

* Language & Anonymity: Submissions must be written in English and formatted for anonymous review (please remove author names and any identifying information). * Length Requirements: Short paper submissions should not exceed 5 pages (excluding references) following the provided template. Poster abstracts should not exceed 300 words (excluding references). References for poster abstracts are not counted in the word limit. * Templates: To ensure a uniform appearance, authors must use the official conference templates. Templates are available for both Microsoft Word and LaTeX (stand-alone and Overleaf template) on the conference website. Please do not alter margins, font sizes, or other format settings in the templates. Submissions not adhering to the template format may be returned for revision.

Word template (.docx)https://cmc2026.org/assets/cmc-2026-word-template.docxLaTeX template (.zip)https://cmc2026.org/assets/CMC2026_Template.zipOpen in Overleaf (template)https://www.overleaf.com/latex/templates/cmc2026-template/pthnqkkzpyss How to Submit All submissions should be made electronically through the conference’s online submission system (https://conftool.net/cmc2026). A dedicated submission link will be provided on the conference website when submissions open. If you do not already have an account on the chosen platform, you will need to create one prior to submission. When submitting, please select the appropriate track for your contribution (short paper or poster/demo abstract). You will be asked to enter title, abstract, author information (for camera-ready version), and keywords. Ensure that the PDF of your submission is anonymized for review. For any questions regarding the submission process or topic suitability, please contact the organizers at cmc2026@oulu.fimailto:cmc2026@oulu.fi. We look forward to your contributions and to welcoming you to the conference! The organizing committee

* Steven Coats * Maarit Siromaa * Jarkko Toikkanen * Hanne Juntunen

References

* Grzenkowicz, M., & Wildfeuer, J. (2025). Addressing TikTok’s multimodal complexity: A multi-level annotation scheme for the audio-visual design of short video content. Digital Scholarship in the Humanities, 40(4), 1143–1166. https://doi.org/10.1093/llc/fqaf047 * Nguyen, V. C., Jain, M., Chauhan, A., Soled, H. J., Lesmes, S. A., Li, Z., Birnbaum, M. L., Tang, S. X., Kumar, S., & De Choudhury, M. (2025). Supporters and Skeptics: LLM-Based Analysis of Engagement with Mental Health (Mis)Information Content on Video-Sharing Platforms. Proceedings of the International AAAI Conference on Web and Social Media, 19, 1329–1345. https://doi.org/10.1609/icwsm.v19i1.35875

© 2025 CMC-Corpora Conference Committee (CC BY 4.0 license for this Call for Papers)