A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement
Open accessThe 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
Cites
Statistics
Figures




Verification
Claims the paper makes
0 Valid · 1 Not valid · 28 Not checked · 70 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For 'distance', words such as 'relationship', 'crying' or 'snap' came to the forefront, suggesting a link to emotional ties and online communication, whereas 'pov' was associated with 'boyfriend', 'bestie' or 'family', reinforcing the emphasis on personal or social stories.”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In particular, for views and comments, there is a more marked increase in the AFINN mean in the > MED group, which may indicate a more intense emotional charge of hooks that reach higher levels of interaction.”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
hedgedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Conversely, hooks with above-median likes tend to employ terms related to individual narratives and life transitions, with”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For 'distance', words such as 'relationship', 'crying' or 'snap' came to the forefront, suggesting a link to emotional ties and online communication, whereas 'pov' was associated with 'boyfriend', 'bestie' or 'family', reinforcing the emphasis on personal or social stories.”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the group with fewer likes, terms associated with interpersonal relationships and discovery, such as”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
40 more claims
Create a free account to see all 99 claims and to verify the 26 references still open.
- It may state two separate claims as one. 21
- The quote only partly states this claim. 2
- Probably not a substantial claim. 40
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.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
“This distinction in linguistic composition between the two categories, defined by median view counts, supports the hypothesis that particular lexical choices significantly influence the reach and engagement of content on digital platforms.”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
“Hypotheses H1a, H1b and H1c, which assumed a statistically significant correlation between the occurrence of selected lexical items in hooks and the level of engagement (measured by the number of views, likes and comments), did not find statistically significant relationships”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 3. Materials and methods.
“All analyses were performed in R version 4.4.2Pile of Leaves (R Core Team, 2024).”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > References
“R Core Team. (2024). Language and Environment for Statistical Computing. Foundation for Statistical Computing, 4.5.2.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 4. Results.
“categorizing hooks on the basis of median likes (< MED vs. > MED), as illustrated in Figure 2”
§ A Lexical and Sentiment Analysis of TikTok Hooks and Their Influence on Digital Engagement > 6. Conclusions.
“Figure 2. Wordcloud by the median likelihood metric.”
Citations
Cites
Users of the world, unite! The challenges and opportunities of Social Media
Kaplan, A. M., & Haenlein, M. (2010) · Business Horizons · doi:10.1016/j.bushor.2009.09.003 · Cited by 17,875
Opinion mining and sentiment analysis
Pang, B., & Lee, L. (2008) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000011 · Cited by 6,372
VADER: a parsimonious rule-based model for sentiment analysis of social media text
Hutto, C., & Gilbert, E. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14550 · Cited by 6,087
Understanding customer experience throughout the customer journey
Lemon, K. N., & Verhoef, P. C. (2016) · Journal of Marketing · doi:10.1509/jm.15.0420 · Cited by 5,765
Social media? Get serious! Understanding the functional building blocks of social media
Kietzmann, J. H., Hermkens, K., McCarthy, I. P., & Silvestre, B. S. (2011) · Business Horizons · doi:10.1016/j.bushor.2011.01.005 · Cited by 4,970
Dwivedi, Y. K., Ismagilova, E., Hughes, D. L., Carlson, J., Filieri, R., Jacobson, J., Jain, V., Karjaluoto, H., Kefi, H., Krishen, A. S., et al. (2021) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2020.102168 · Cited by 4,608
Consumer Brand Engagement in Social Media: Conceptualization, Scale Development and Validation
Hollebeek, L. D., Glynn, M. S., & Brodie, R. J. (2014) · Journal of Interactive Marketing · doi:10.1016/j.intmar.2013.12.002 · Cited by 3,276
What Makes Online Content Viral?
Berger, J., & Milkman, K. L. (2012) · Journal of Marketing Research · doi:10.1509/jmr.10.0353 · Cited by 3,178
The future of social media in marketing
Appel, G., Grewal, L., Hadi, R., & Stephen, A. T. (2020) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-019-00695-1 · Cited by 1,893
Why people use social media: a uses and gratifications approach
Whiting, A., & Williams, D. (2013) · Qualitative Market Research: An International Journal · doi:10.1108/qmr-06-2013-0041 · Cited by 1,810
We’re all connected: The power of the social media ecosystem
Hanna, R., Rohm, A., & Crittenden, V. L. (2011) · Business Horizons · doi:10.1016/j.bushor.2011.01.007 · Cited by 1,650
Emotions and Information Diffusion in Social Media—Sentiment of Microblogs and Sharing Behavior
Stieglitz, S., & Dang-Xuan, L. (2013) · Journal of Management Information Systems · doi:10.2753/mis0742-1222290408 · Cited by 1,604
Alhabash, S., & Ma, M. (2017) · Social Media + Society · doi:10.1177/2056305117691544 · Cited by 820
Engagement with Social Media and Social Media Advertising: The Differentiating Role of Platform Type
Voorveld, H. A. M., van Noort, G., Muntinga, D. G., & Bronner, F. (2018) · Journal of Advertising · doi:10.1080/00913367.2017.1405754 · Cited by 819
The attention economy and the Net
Goldhaber, M. H. (1997) · First Monday · doi:10.5210/fm.v2i4.519 · Cited by 805
Social Media Metrics — A Framework and Guidelines for Managing Social Media
Peters, K., Chen, Y., Kaplan, A. M., Ognibeni, B., & Pauwels, K. (2013) · Journal of Interactive Marketing · doi:10.1016/j.intmar.2013.09.007 · Cited by 657
Mapping Internet Celebrity on TikTok: Exploring Attention Economies and Visibility Labours
Abidin, C. (2020) · Cultural Science Journal · doi:10.5334/csci.140 · Cited by 564
On the psychology of TikTok use: a first glimpse from empirical findings
Montag, C., Yang, H., & Elhai, J. D. (2021) · Frontiers in Public Health · doi:10.3389/fpubh.2021.641673 · Cited by 559
Navigating the New Era of Influencer Marketing: How to be Successful on Instagram, TikTok, & Co.
Haenlein, M., Anadol, E., Farnsworth, T., Hugo, H., Hunichen, J., & Welte, D. (2020) · California Management Review · doi:10.1177/0008125620958166 · Cited by 548
Highfield, T., & Leaver, T. (2016) · Communication Research and Practice · doi:10.1080/22041451.2016.1155332 · Cited by 542
Social media engagement behavior: A framework for engaging customers through social media content
Dolan, R., Conduit, J., Frethey-Bentham, C., Fahy, J., & Goodman, S. (2019) · European Journal of Marketing · doi:10.1108/ejm-03-2017-0182 · Cited by 519
Kaye, D. B. V., Chen, X., & Zeng, J. (2021) · Mobile Media & Communication · doi:10.1177/2050157920952120 · Cited by 500
Omar, B., & Dequan, W. (2020) · International Journal of Interactive Mobile Technologies (iJIM) · doi:10.3991/ijim.v14i04.12429 · Cited by 493
Why’s Everyone on TikTok Now? The Algorithmized Self and the Future of Self-Making on Social Media
Bhandari, A., & Bimo, S. (2022) · Social Media + Society · doi:10.1177/20563051221086241 · Cited by 491
Wang, Y. (2020) · Computers in Human Behavior · doi:10.1016/j.chb.2020.106373 · Cited by 424
Faces engage us: photos with faces attract more likes and comments on Instagram
Bakhshi, S., Shamma, D. A., & Gilbert, E. (2014) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/2556288.2557403 · Cited by 399
Karizat, N., Delmonaco, D., Eslami, M., & Andalibi, N. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3476046 · Cited by 339
Kennedy, M. (2020) · European Journal of Cultural Studies · doi:10.1177/1367549420945341 · Cited by 325
Uses and gratifications sought by pre-adolescent and adolescent TikTok consumers
Bucknell Bossen, C., & Kottasz, R. (2020) · Young Consumers · doi:10.1108/yc-07-2020-1186 · Cited by 305
A Survey of Sentiment Analysis: Approaches, Datasets, and Future Research
Tan, K. L., Lee, C. P., & Lim, K. M. (2023) · Applied Sciences · doi:10.3390/app13074550 · Cited by 303
Getting acquainted with social networks and apps: it is time to talk about TikTok
Anderson, K. E. (2020) · Library Hi Tech News · doi:10.1108/lhtn-01-2020-0001 · Cited by 297
Zeng, J., & Abidin, C. (2021) · Information, Communication & Society · doi:10.1080/1369118x.2021.1961007 · Cited by 228
Becoming TikTok Famous: Strategies for Global Brands to Engage Consumers in an Emerging Market
Wahid, R. M., Karjaluoto, H., Taiminen, K., & Asiati, D. I. (2022) · Journal of International Marketing · doi:10.1177/1069031x221129554 · Cited by 209
Cheng, Z., & Li, Y. (2024) · Social Science Computer Review · doi:10.1177/08944393231178603 · Cited by 131
Sentiment Analysis: A Fascinating Problem
Liu, B. (2012) · Synthesis Lectures on Human Language Technologies · doi:10.1007/978-3-031-02145-9_1 · Cited by 120
Analysis of Tik Tok User Behavior from the Perspective of Popular Culture
Hui, Z., & Wang, T. (2019) · doi:10.25236/far.20190301 · Cited by 112
The Reach and Persuasiveness of Viral Video Ads
Tucker, C. E. (2015) · Marketing Science · doi:10.1287/mksc.2014.0874 · Cited by 97
Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations
Zannettou, S., Nemes-Nemeth, O., Ayalon, O., Goetzen, A., Gummadi, K. P., Redmiles, E. M., & Roesner, F. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642433 · Cited by 85
(Monroe) Meng, L., Kou, S., Duan, S., & Bie, Y. (2024) · Journal of Business Research · doi:10.1016/j.jbusres.2024.114874 · Cited by 80
Less is more: Engagement with the content of social media influencers
van der Harst, J. P., & Angelopoulos, S. (2024) · Journal of Business Research · doi:10.1016/j.jbusres.2024.114746 · Cited by 51
Ying, L. J., Chuan, L. T., Rashid, U. K., & Seman, N. A. A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.01.278 · Cited by 46
Naeem, M., Ozuem, W., Ranfagni, S., & Howell, K. E. (2025) · Computers in Human Behavior · doi:10.1016/j.chb.2025.108642 · Cited by 38
Ma, C., Wang, B. W., Dai, L., Guan, X., & Yang, Z. (2024) · Journal of Business Research · doi:10.1016/j.jbusres.2024.115170 · Cited by 33
TikTok and the changing landscape of therapeutic digital spaces of care
Green, J. (2023) · Digital Geography and Society · doi:10.1016/j.diggeo.2023.100077 · Cited by 17
Chen, M., Zhang, X., & Wang, F. (2025) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2024.104213 · Cited by 15
Digital marketing in community-based enterprises: A systematic literature review and research agenda
Tran, T. T. S., Nemeth, N., & Sarker, M. S. I. (2024) · Journal of Open Innovation: Technology, Market, and Complexity · doi:10.1016/j.joitmc.2024.100414 · Cited by 13
(2021) · International journal of communication
Research works printed but not linked: 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.
Cited by
Suurhasko, N. (2026) · UTUPub (University of Turku)
Шевель, А. О. (2026) · Electronic Sumy State University Institutional Repository (Sumy State University)
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
- Publisher
- Sumy State University
- Published
- 2025-12-30
- Volume
- 16
- Issue
- 4
- Pages
- 64
- ISSN
- 2218-4511 (ISSN-L)
- 2227-6718
- OpenAlex
- W7119531365
- Semantic Scholar
- 90bbc6d2d9dd5bbdfe72572ff658cf8710f6ca97
- Cited by
- 2
- References
- 46
- Citations by year
- 2026: 2
- FWCI
- 0.37
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- 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
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.