{"id":{"repo_id":"auckland-ms","oai_identifier":"oai:researchspace.auckland.ac.nz:2292/74713"},"canonical_url":"https://search.dev.ndltd.org/etd/auckland-ms/oai:researchspace.auckland.ac.nz:2292/74713","repository":{"repo_id":"auckland-ms","name":"University of Auckland","base_url":"https://researchspace.auckland.ac.nz/server/oai/request"},"display":{"title":"Decoding Emoji Signals: Attention, Information, and Divergence in Financial Markets","abstract":"This thesis investigates the predictive role of emoji-based investor opinion and divergence derived from Twitter data in shaping financial market behavior. It presents an integrated examination of three empirical studies, each addressing how emoji-based signals influence asset pricing and investor behavior across different asset classes, event types, and behavioral contexts. The first study constructs a novel emoji-based opinion indicator using over 48 million tweets referencing S&P 500 companies from 2013 to 2022. The analysis reveals that emoji opinion significantly predicts future stock returns, even after controlling for conventional text-based opinion measures. A trading strategy based on this indicator yields an annual risk-adjusted return of 28.64%, highlighting the economic significance of emoji opinion. Extending this approach to 52 million cryptocurrency-related tweets, the study finds an even stronger predictive effect on crypto returns—likely due to the heightened market inefficiency and retail investor dominance in crypto markets. The second study focuses on the role of emoji opinion in forecasting corporate earnings outcomes. It investigates whether emojis embedded in tweets posted prior to earnings announcements can predict both earnings surprises and announcement returns. Results indicate that emoji opinion reliably forecasts both, beyond the explanatory power of text-based opinion and media coverage. The effect is particularly pronounced in information-scarce environments and among retail-dominated stocks, suggesting that emojis serve as salient, intuitive cues in the absence of rich fundamental data. The third study explores emoji-based divergence as a distinct form of investor heterogeneity that captures emotional nuance and divergence beyond textual opinion. The findings show that emoji-based divergence correlates strongly with abnormal trading volume and significantly predicts future stock returns. These effects are amplified in highly engaged posts and within more homogenous investor communities. Even after accounting for text-based divergence and investor attention, emoji-based divergence remains a robust and independent signal of market activity. Together, these studies demonstrate the value of emoji-based signals in enhancing our understanding of financial markets. This thesis contributes to the emerging literature on alternative data by showcasing the informational content embedded in emojis and their relevance for predicting asset price movements in the digital era.","abstract_html":"This thesis investigates the predictive role of emoji-based investor opinion and divergence derived from Twitter data in shaping financial market behavior. It presents an integrated examination of three empirical studies, each addressing how emoji-based signals influence asset pricing and investor behavior across different asset classes, event types, and behavioral contexts. The first study constructs a novel emoji-based opinion indicator using over 48 million tweets referencing S&P 500 companies from 2013 to 2022. The analysis reveals that emoji opinion significantly predicts future stock returns, even after controlling for conventional text-based opinion measures. A trading strategy based on this indicator yields an annual risk-adjusted return of 28.64%, highlighting the economic significance of emoji opinion. Extending this approach to 52 million cryptocurrency-related tweets, the study finds an even stronger predictive effect on crypto returns—likely due to the heightened market inefficiency and retail investor dominance in crypto markets. The second study focuses on the role of emoji opinion in forecasting corporate earnings outcomes. It investigates whether emojis embedded in tweets posted prior to earnings announcements can predict both earnings surprises and announcement returns. Results indicate that emoji opinion reliably forecasts both, beyond the explanatory power of text-based opinion and media coverage. The effect is particularly pronounced in information-scarce environments and among retail-dominated stocks, suggesting that emojis serve as salient, intuitive cues in the absence of rich fundamental data. The third study explores emoji-based divergence as a distinct form of investor heterogeneity that captures emotional nuance and divergence beyond textual opinion. The findings show that emoji-based divergence correlates strongly with abnormal trading volume and significantly predicts future stock returns. These effects are amplified in highly engaged posts and within more homogenous investor communities. Even after accounting for text-based divergence and investor attention, emoji-based divergence remains a robust and independent signal of market activity. Together, these studies demonstrate the value of emoji-based signals in enhancing our understanding of financial markets. This thesis contributes to the emerging literature on alternative data by showcasing the informational content embedded in emojis and their relevance for predicting asset price movements in the digital era.","abstract_has_math":false,"creators":["Liu, Xiaozhou"],"institution":"ResearchSpace@Auckland","degree_name":"PhD","degree_level":"Doctoral","degree_discipline":"Finance","degree_department":null,"school":null,"contributors":[],"advisors":["Lee, John","Jayasuriya, Dulani"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-07-24T01:04:52Z","subjects":["Asset Pricing","Behavioural Finance","Investor Sentiment","Social Media"],"languages":[],"rights":["Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated."],"rights_urls":["https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2292/74713","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lee, John","Jayasuriya, Dulani"]},{"key":"dc:creator","label":"Author","values":["Liu, Xiaozhou"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-02-17T23:58:42Z"]},{"key":"dc:date.issued","label":"Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["ResearchSpace@Auckland"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Finance"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_name","label":"Degree Name","values":["PhD"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["The University of Auckland"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Asset Pricing","Behavioural Finance","Investor Sentiment","Social Media"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated."]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2292/74713"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis investigates the predictive role of emoji-based investor opinion and divergence derived from Twitter data in shaping financial market behavior. It presents an integrated examination of three empirical studies, each addressing how emoji-based signals influence asset pricing and investor behavior across different asset classes, event types, and behavioral contexts. The first study constructs a novel emoji-based opinion indicator using over 48 million tweets referencing S&P 500 companies from 2013 to 2022. The analysis reveals that emoji opinion significantly predicts future stock returns, even after controlling for conventional text-based opinion measures. A trading strategy based on this indicator yields an annual risk-adjusted return of 28.64%, highlighting the economic significance of emoji opinion. Extending this approach to 52 million cryptocurrency-related tweets, the study finds an even stronger predictive effect on crypto returns—likely due to the heightened market inefficiency and retail investor dominance in crypto markets. The second study focuses on the role of emoji opinion in forecasting corporate earnings outcomes. It investigates whether emojis embedded in tweets posted prior to earnings announcements can predict both earnings surprises and announcement returns. Results indicate that emoji opinion reliably forecasts both, beyond the explanatory power of text-based opinion and media coverage. The effect is particularly pronounced in information-scarce environments and among retail-dominated stocks, suggesting that emojis serve as salient, intuitive cues in the absence of rich fundamental data. The third study explores emoji-based divergence as a distinct form of investor heterogeneity that captures emotional nuance and divergence beyond textual opinion. The findings show that emoji-based divergence correlates strongly with abnormal trading volume and significantly predicts future stock returns. These effects are amplified in highly engaged posts and within more homogenous investor communities. Even after accounting for text-based divergence and investor attention, emoji-based divergence remains a robust and independent signal of market activity. Together, these studies demonstrate the value of emoji-based signals in enhancing our understanding of financial markets. This thesis contributes to the emerging literature on alternative data by showcasing the informational content embedded in emojis and their relevance for predicting asset price movements in the digital era."]},{"key":"dc:title","label":"Title","values":["Decoding Emoji Signals: Attention, Information, and Divergence in Financial Markets"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lee, John","Jayasuriya, Dulani"],"dc:creator":["Liu, Xiaozhou"],"dc:date.accessioned":["2026-02-17T23:58:42Z"],"dc:date.issued":["2026"],"dc:description.abstract":["This thesis investigates the predictive role of emoji-based investor opinion and divergence derived from Twitter data in shaping financial market behavior. It presents an integrated examination of three empirical studies, each addressing how emoji-based signals influence asset pricing and investor behavior across different asset classes, event types, and behavioral contexts. The first study constructs a novel emoji-based opinion indicator using over 48 million tweets referencing S&P 500 companies from 2013 to 2022. The analysis reveals that emoji opinion significantly predicts future stock returns, even after controlling for conventional text-based opinion measures. A trading strategy based on this indicator yields an annual risk-adjusted return of 28.64%, highlighting the economic significance of emoji opinion. Extending this approach to 52 million cryptocurrency-related tweets, the study finds an even stronger predictive effect on crypto returns—likely due to the heightened market inefficiency and retail investor dominance in crypto markets. The second study focuses on the role of emoji opinion in forecasting corporate earnings outcomes. It investigates whether emojis embedded in tweets posted prior to earnings announcements can predict both earnings surprises and announcement returns. Results indicate that emoji opinion reliably forecasts both, beyond the explanatory power of text-based opinion and media coverage. The effect is particularly pronounced in information-scarce environments and among retail-dominated stocks, suggesting that emojis serve as salient, intuitive cues in the absence of rich fundamental data. The third study explores emoji-based divergence as a distinct form of investor heterogeneity that captures emotional nuance and divergence beyond textual opinion. The findings show that emoji-based divergence correlates strongly with abnormal trading volume and significantly predicts future stock returns. These effects are amplified in highly engaged posts and within more homogenous investor communities. Even after accounting for text-based divergence and investor attention, emoji-based divergence remains a robust and independent signal of market activity. Together, these studies demonstrate the value of emoji-based signals in enhancing our understanding of financial markets. This thesis contributes to the emerging literature on alternative data by showcasing the informational content embedded in emojis and their relevance for predicting asset price movements in the digital era."],"dc:identifier.uri":["https://hdl.handle.net/2292/74713"],"dc:publisher":["ResearchSpace@Auckland"],"dc:rights":["Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated."],"dc:rights.uri":["https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm"],"dc:subject":["Asset Pricing","Behavioural Finance","Investor Sentiment","Social Media"],"dc:title":["Decoding Emoji Signals: Attention, Information, and Divergence in Financial Markets"],"dc:type":["Thesis"],"thesis:degree_discipline":["Finance"],"thesis:degree_level":["Doctoral"],"thesis:degree_name":["PhD"],"thesis:institution_name":["The University of Auckland"]},"updated_at":"2026-07-24T01:04:52Z"}