TY - GEN

T1 - Automatic Annotation of Discourse and Speech Formulas in Internet Communication: A Telegram Comment Corpus

AU - Попова, Татьяна Ивановна

AU - Масленикова, Александра

N1 - Conference code: 27

PY - 2026

Y1 - 2026

N2 - This article presents a system for the automatic processing of user comments aimed at annotating speech and discourse formulas that actively function in everyday interaction, including digital communication. A Python-based program using the Telegram API was developed to automate the collection, filtering, and annotation of empirical data. In addition to building a user corpus, the study also included the evaluation of automatic processing results. The source material was drawn from the Telegram news channel Fontanka SPB Online. As a result of automatic processing, 70 speech and discourse formulas were extracted and grouped based on their source lexicons. The classification of the examined multiword units was grounded in the findings of two research projects: the construction of the Pragmaticon in Moscow and the annotation of stable multiword units in Saint Petersburg. The implementation of automatic annotation enabled the identification of formulas with a high pragmatic load and captured their specific functions in internet communication. For example, semantic irony was observed in the use of formulas such as ‘khorosho’ (‘fine’) and ‘bez problem’ (‘no problem’), which traditionally indicate agreement. The study identified the most frequent types of user responses reflected by the formulas: affirmation and negation. The results demonstrate the potential of the automatic approach for describing speech and discourse formulas in digital discourse and highlight the need to refine existing classifications of speech act.

AB - This article presents a system for the automatic processing of user comments aimed at annotating speech and discourse formulas that actively function in everyday interaction, including digital communication. A Python-based program using the Telegram API was developed to automate the collection, filtering, and annotation of empirical data. In addition to building a user corpus, the study also included the evaluation of automatic processing results. The source material was drawn from the Telegram news channel Fontanka SPB Online. As a result of automatic processing, 70 speech and discourse formulas were extracted and grouped based on their source lexicons. The classification of the examined multiword units was grounded in the findings of two research projects: the construction of the Pragmaticon in Moscow and the annotation of stable multiword units in Saint Petersburg. The implementation of automatic annotation enabled the identification of formulas with a high pragmatic load and captured their specific functions in internet communication. For example, semantic irony was observed in the use of formulas such as ‘khorosho’ (‘fine’) and ‘bez problem’ (‘no problem’), which traditionally indicate agreement. The study identified the most frequent types of user responses reflected by the formulas: affirmation and negation. The results demonstrate the potential of the automatic approach for describing speech and discourse formulas in digital discourse and highlight the need to refine existing classifications of speech act.

KW - Automatic Annotation

KW - Statistical Analysis

KW - Modern Russian

KW - Corpus Linguistics

KW - Discourse Formulas

KW - Internet Discourse

KW - Internet Comment

KW - Speech Formulas

KW - Automatic Annotation

KW - Corpus Linguistics

KW - Discourse Formulas

KW - Internet Comment

KW - Internet Discourse

KW - Modern Russian

KW - Speech Formulas

KW - Statistical Analysis

UR - https://link.springer.com/chapter/10.1007/978-3-032-07956-5_20

UR - https://www.mendeley.com/catalogue/da481d95-1e08-3370-9a79-a221343755c2/

U2 - 10.1007/978-3-032-07956-5_20

DO - 10.1007/978-3-032-07956-5_20

M3 - статья в сборнике материалов конференции

SN - 9783032079558

T3 - Lecture Notes in Computer Science

SP - 278

EP - 292

BT - Speech and Computer. SPECOM 2025

PB - Springer Nature

CY - Szeged, Hungary

T2 - 27th International Conference on Speech and Computer

Y2 - 13 October 2025 through 14 October 2025

ER -