A Study of Multimodal Banner Discourse on Chinese E-Commerce Websites From the Perspective of Discourse Information
Bibliographic record
Abstract
The banner ads on the e-commerce websites offer the information of new goods, best sellers, and promotions etc., which aim to attract the consumers, arouse their desire for shopping, and then guide them to the pages of advertised products. In linguistic sense, a banner is multimodal ads discourse being composed of text and images. So far, most of the multimodal studies of ad discourse take traditional printed ads other than banners as research object, and analysis is conducted, with metafunctions of language from the systemic functional linguistics as the basis, and visual grammar by Kress & van Leeuwen as the theoretical framework, to describe their representational meaning, interactive meaning or compositional meaning as well as meaning-construction patterns in ad discourse. Supported by the ideas of defining ads as one way to transmit information and consuming behavior as the course of processing information, the banner ads sampled from three most popular Chinese e-commerce websites of amazon.cn, TMALL.COM, and JD.COM are analyzed in this paper to demonstrate the characteristics of information structure of both language and non-language discourse in banner ad discourse, and further the way in which images are interrelated with text through information to fulfil the banner’s shopping guidance performance. The analysis also provides proof that the effectiveness of banners can be improved through perfecting the way in which text and images are interrelated.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.004 | 0.004 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".