{"paper_id":"2508.15825","title":"Enhancing Cryptocurrency Sentiment Analysis with Multimodal Features","authors":["Chenghao Liu","Aniket Mahanti","Ranesh Naha","Guanghao Wang","Erwann Sbai"],"paper_date":"2025-08-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.15825v2","page_url":"https://thequant.space/flowcharts/enhancing-cryptocurrency-sentiment-analysis-with-multimodal/","scores":{"empirical_rigor":7.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a multimodal framework that analyzes TikTok video‑based sentiment alongside Twitter text‑based sentiment to improve cryptocurrency market forecasting.","quote":"We introduce a framework for analyzing TikTok video-based sentiment compared to Twitter text-based sentiment in cryptocurrency sentiment analysis.","summary":"As cryptocurrencies gain popularity, the digital asset marketplace becomes increasingly significant. Understanding social media signals offers valuable insights into investor sentiment and market dynamics. Prior research has predominantly focused on text-based platforms such as Twitter. However…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"All time‑series (price, volume, sentiment) are stationary after first differencing.","type":"statistical","stated":"explicit","quote":"that all-time series are stationary at the first difference. These preliminary results justify the use of DCC-GARCH-based connectedness models in the study"}]},"datasets":{"status":"available","items":[{"name":"Twitter data","provider":"Tweepy (Twitter API)","kind":"text-news","access":"public","period":"Nov 8, 2021 to Mar 13, 2024","universe":"public Tweets related to cryptocurrency","quote":"Twitter Data: From November 8, 2021 to March 13, 2024, 519,208 public Tweets related to cryptocurrency were collected as JSON line objects using a Tweepy-based web crawler.","known_id":"twitter"},{"name":"TikTok data","provider":"TikTok API","kind":"alternative","access":"public","period":null,"universe":"15,348 video posts from top 10 cryptocurrency influencers","quote":"TikTok Data: A dataset of 15,348 TikTok video posts was collected using a multi step method adapted from Cheng and Li."}],"known":[{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"Results Here, we use MOMENTTwitter as our baseline, given extensive research leveraging Twitter sentiment for cryptocurrency forecasting [77, 47, 89, 90].","mentions":89,"used_in":5}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Integrating TikTok and Twitter sentiment improves cryptocurrency return and volume forecasts by up to 20%.","kind":"predictive-accuracy","quote":"Our findings show combining TikTok and Twitter sentiment enhances crypto return and volume forecasts by up to 20%, with TikTok alone improving short-term Dogecoin predictions by 35%."},{"finding":"TikTok video‑based sentiment strongly predicts short‑term speculative assets such as Dogecoin, while Twitter text‑based sentiment aligns better with long‑term dynamics like Bitcoin.","kind":"predictive-accuracy","quote":"TikTok sentiment particularly influences short-term speculative trends, while Twitter sentiment aligns better with long-term market dynamics."},{"finding":"Dogecoin is identified as the primary transmitter of volume spillovers, whereas stablecoins show limited responsiveness to social‑media sentiment.","kind":"statistical","quote":"Dogecoin is identified as the primary transmitter of volume spillovers, whereas stablecoins exhibit limited responsiveness to social media sentiment."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":23,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T16:37:41Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}