Using tweet phrases to predict the transition from migration intentions to real-life movements

Anna Janicka () and Hayk Amirkhanyan
Additional contact information
Anna Janicka: University of Warsaw, Faculty of Economic Sciences
Hayk Amirkhanyan: University of Warsaw, Faculty of Economic Sciences

No 2026-23, Working Papers from Faculty of Economic Sciences, University of Warsaw

Abstract: Understanding the transition from migration intentions to actual movements remains a challenge in demographic research, often hampered by a persistent intention-behavior gap. This research examines how linguistic variations in individuals' stated migration intentions, particularly on social media, help predict actual movements. We hypothesize that the specific phrasing of the intention reflects the strength and proximity to realization. To verify this claim, we compiled a unique dataset based on migration-related tweets from Polish users posted between 2006 and 2021, identifying potential migrants via Polish keywords that indicated some form of migration intent. The collected statements were manually categorized for linguistic nuances and contextual factors. Actual migration was subsequently tracked by detecting significant country changes (minimum 30 or 180 days) in users' geotagged tweet histories, and logistic regression models were applied to assess the predictive power of different formulations. Our findings demonstrate that the linguistic phrasing of migration intentions correlates significantly with their realization: users employing “planning” keywords were most likely to migrate, while those expressing mere “preferences” were the least likely. Additionally, intentions communicated through multiple tweets, as well as those linked to concrete goals, such as education, positively predicted actual movement. Conversely, tweets with negative contexts, hypothetical conditions, or perceived obstacles were related to a reduced actual migration probability. This study empirically confirms that subtle linguistic variations and contextual elements within spontaneous social media expressions may be treated as indicators of migration intention strength and its likelihood of translating into actual behavior. Our results highlight the importance of differentiating intention forms to enhance migration predictions and refine future survey designs.

Keywords: migration intentions; migration behavior; migration decision-making; intention-behavior gap; social media analysis; Twitter data; geolocated data; linguistic cues; migration prediction; human mobility; Poland (search for similar items in EconPapers)
JEL-codes: C55 D83 D91 J10 J61 (search for similar items in EconPapers)
Pages: 32 pages
Date: 2026
New Economics Papers: this item is included in nep-mig
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.wne.uw.edu.pl/download_file/02a8c336-8 ... 9a-9ac9cfada681/4282 First version, 2026 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:war:wpaper:2026-23

Access Statistics for this paper

More papers in Working Papers from Faculty of Economic Sciences, University of Warsaw Contact information at EDIRC.
Bibliographic data for series maintained by Jacek Rapacz ().