Purchase Intentions on Social Media as Predictors of Consumer Spending


The paper addresses the problem of forecasting consumer expenditure from social media data. Previous research of the topic exploited the intuition that search engine traffic reflects purchase intentions and constructed predictive models of consumer behaviour from search query volumes. In contrast, we derive predictors from explicit expressions of purchase intentions found in social media posts. Two types of predictors created from these expressions are explored: those based on word embeddings and those based on topical word clusters. We introduce a new clustering method, which takes into account temporal co-occurrence of words, in addition to their semantic similarity, in order to create predictors relevant to the forecasting problem. The predictors are evaluated against baselines that use only macroeconomic variables, and against models trained on search traffic data. Conducting experiments with three different regression methods on Facebook and Twitter data, we find that both word embeddings and word clusters help to reduce forecasting errors in comparison to purely macroeconomic models. In most experimental settings, the error reduction is statistically significant, and is comparable to error reduction achieved with search traffic variables.

Divisions: College of Business and Social Sciences > Aston Business School > Operations & Information Management
Additional Information: Copyright 2020, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Event Title: 14th International Conference on Web and Social Media
Event Type: Other
Event Dates: 2020-06-08 - 2020-06-11
Uncontrolled Keywords: social media,Natural Language Processing,Macroeconomic forecasting,Artificial Intelligence,Economics, Econometrics and Finance (miscellaneous)
Last Modified: 17 Jun 2024 08:33
Date Deposited: 19 May 2020 07:03
Full Text Link:
Related URLs: https://www.icwsm.org/2020/ (Publisher URL)
PURE Output Type: Conference contribution
Published Date: 2020-06-08
Accepted Date: 2020-05-01
Authors: Pekar, Viktor (ORCID Profile 0000-0002-9664-1675)



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record