CoChat

A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement

Open access
Nastisin, Ludovit, Mruz, Ondrej, Gavura, Stefan, Mruzova, Yvette Nataly · 2025 · Marketing and Management of Innovations

The DOI matches its Crossref record; 46 of the 47 references it cites were found in a registry or an index; none of the 35 sources its claims cite is checked for support yet.

Abstract

This study investigates the relationship between the linguistic and sentimental characteristics of TikTok hooks, which are defined as the brief opening seconds of short-form video content, and subsequent digital engagement levels. The research aims to determine whether the frequency and contextual use of specific lexical features, as well as the emotional tone present in hooks, are associated with key interaction metrics on TikTok, such as views, likes, and comments. To achieve this objective, a dataset of 4983 hooks was compiled by scraping publicly available TikTok content published between January 2020 and December 2022. Audio-to-text transcription facilitated the extraction of linguistic information, which was subsequently analysed via three sentiment analysis methods: Sentimentr, AFINN, and Syuzhet. These methods were employed to capture contextual polarity, affective intensity, and emotional variation. Statistical analyses included Spearman’s correlation tests to assess the relationship between lexical frequencies and engagement metrics, as well as Wilcoxon’s nonparametric tests to compare sentiment profiles between hooks with above- and below-median engagement levels. The findings indicate no statistically significant correlation between the selected lexical features and any of the interaction metrics, suggesting that simple word frequency is not a reliable predictor of user engagement. However, significant differences were observed in sentiment profiles, particularly for the number of views, implying that emotionally charged hooks may be more effective at capturing initial audience attention and may benefit from early algorithmic amplification. These results are consistent with theoretical perspectives from the attention economy, which emphasize the role of emotional salience in shaping user behaviour during the initial moments of content exposure. Several methodological limitations are acknowledged, including potential inaccuracies in audio-to-text transcription, the exclusion of multimodal features such as visual and audio cues, and reliance on lexicon-based sentiment tools that may not fully capture nuanced emotional expression. Future research should incorporate multimodal analysis, semantic modelling, and experimental designs to more comprehensively examine how linguistic, visual, auditory, and algorithmic factors collectively influence engagement patterns on short-form video platforms.

Overview

CoChat Summary

TL;DR

This study examines whether the lexical content and emotional tone of TikTok "hooks" (the opening seconds of short-form videos) predict engagement, using 4,983 transcribed hooks scraped from public TikTok content. It finds no significant correlation between word frequency and views, likes, or comments, but does find significant sentiment differences between above- and below-median hooks for views.

Key findings

  • No statistically significant correlation was found between the frequency of selected lexical items and any engagement metric: views (Spearman rho = 0.0208, p = 0.1672), likes (rho = 0.014, p = 0.353), comments (rho = 0.0026, p = 0.9013), so H1a–H1c were not supported.
  • H2 was partially confirmed: Wilcoxon tests showed significant sentiment differences between above- and below-median hooks for views (AFINN p < 0.001; Syuzhet p = 0.001), but not for likes (AFINN p = 0.323; Syuzhet p = 0.055) or comments (AFINN p = 0.493; Syuzhet p = 0.184).
  • Mean AFINN sentiment was higher in the above-median group across metrics (views: 0.81 below vs. 1.11 above; likes: 0.70 vs. 1.22; comments: 0.43 vs. 1.88), while Sentimentr and Syuzhet differences were less pronounced.
  • Lexically, below-median-view hooks were dominated by relational terms such as "friends" and "found," while above-median-view hooks featured "distance" and "pov"; the authors interpret "POV" and similar framing terms as positioning viewers within a narrative context.

Methods

  • Dataset of 4,983 hooks scraped from publicly available TikTok content published January 2020–December 2022, English-language only, with no thematic filtering; hooks were transcribed via audio-to-text and paired with views, likes, and comments.
  • Three lexicon-based sentiment tools were applied — Sentimentr, AFINN, and Syuzhet — chosen for complementary handling of context, polarity, and emotional variation; VADER, NRC, and transformer models were excluded for inconsistent performance on ultrashort inputs.
  • Analysis in R 4.4.2 used Spearman's rho for lexical-frequency/engagement associations and Wilcoxon nonparametric tests with a median split to compare sentiment profiles between higher- and lower-engagement hooks; preprocessing included lowercasing, punctuation/artifact removal, and listwise deletion of incomplete records.

Limitations

  • Stated: the 4,983-entry dataset may not represent all TikTok videos, limiting generalizability; audio-to-text transcription may contain errors for brief, colloquial, or overlapping speech, and transcription accuracy could not be systematically assessed.
  • Stated: multimodal features (video duration, audio tracks, trending sounds, editing style, visual composition) were deliberately excluded, and the presence of a human face may be a confounding variable; word clouds capture frequency but not semantic relationships.
  • Stated: the analysis establishes association, not causality — sentiment may correlate with views through algorithmic mediation or unrelated contextual factors; experimental or longitudinal designs would be needed.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.21272/mmi.2025.4-04

Cites

46 of 47 references verified0 citation errors · 1 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Wordcloud by Median Views metric.
Figure 1 Wordcloud by Median Views metric.CC-BY · From the PDF
Figure 2 Wordcloud by the median likelihood metric.
Figure 2 Wordcloud by the median likelihood metric.CC-BY · From the PDF
Figure 3 Wordcloud by Median Comments metric. Source: Developed by the authors.
Figure 3 Wordcloud by Median Comments metric. Source: Developed by the authors.CC-BY · From the PDF
Figure 4 Most frequent associations with selected keywords. Source: Developed by the authors.
Figure 4 Most frequent associations with selected keywords. Source: Developed by the authors.CC-BY · From the PDF

Verification

Claims the paper makes

0 Valid · 1 Not valid · 28 Not checked · 70 Own results and interpretations

40 more claims

Create a free account to see all 99 claims and to verify the 26 references still open.

See all claims — free account
  • It may state two separate claims as one. 21
  • The quote only partly states this claim. 2
  • Probably not a substantial claim. 40

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

3 of 3

Citations

Cites

Show all 47 references

Research works printed but not linked: 1

  1. Bhandari, A., & Bimo, S. (2022). Why’s everyone on TikTok now? The algorithmization of identity on TikTok. New Media & Society, 24(10), 2268–2285.

Metadata

Authors
Nastisin, L., Mruz, O., Gavura, S., & Mruzova, Y. N.
Affiliations
  • University of Presov, Slovakia
  • University of Prešov (SK)
  • Technical University of Košice
Venue
Marketing and Management of Innovations
Published
2025-12-30
Volume
16
Issue
4
Pages
64
ISSN
  • 2218-4511 (ISSN-L)
  • 2227-6718
OpenAlex
W7119531365
Cited by
2
References
46
Citations by year
2026: 2
FWCI
0.37
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Marketing and Management of Innovations (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Vedecká Grantová Agentúra MŠVVaŠ SR a SAV
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
  • Social Sciences › Business, Management and Accounting › Marketing › Digital Marketing and Social Media
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
Keywords
short-form video, user engagement, sentiment analysis, lexical features, word frequency, emotional salience, attention economy, algorithmic amplification, social media content

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-11-20, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-11-20 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement. https://app.cochat.ai/papers/10.21272/mmi.2025.4-04
The paper
Nastisin, L., Mruz, O., Gavura, S., & Mruzova, Y. N. (2025). A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement. Marketing and Management of Innovations. https://doi.org/10.21272/mmi.2025.4-04

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.