Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media

Viktor Pekar, Jane Binner

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Consumer spending is a vital macroeconomic indicator. In this paper we present
a novel method for predicting future consumer spending from social media data. In contrast to previous work that largely relied on sentiment analysis, the proposed method models consumer spending from purchase intentions found on social media. Our experiments with time series analysis models and machine-learning regression models reveal utility of this data for making short-term forecasts of consumer spending: for three- and seven-day horizons, prediction variables derived from social media help to improve forecast accuracy by 11% to 18% for all the three models, in comparison to models that used only autoregressive predictors.
Original languageEnglish
Title of host publicationProceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Place of PublicationCopenhagen, Denmark
PublisherAssociation for Computational Linguistics
Pages92-101
DOIs
Publication statusPublished - 8 Sep 2017

Fingerprint

Social media
Consumer spending
Purchase intention
Regression model
Machine learning
Macroeconomic indicators
Prediction
Predictors
Sentiment analysis
Forecast accuracy
Experiment
Time series analysis

Bibliographical note

© 2017 The Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.

Cite this

Pekar, V., & Binner, J. (2017). Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media. In Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (pp. 92-101). Copenhagen, Denmark: Association for Computational Linguistics. https://doi.org/10.18653/v1/W17-52
Pekar, Viktor ; Binner, Jane. / Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media. Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Copenhagen, Denmark : Association for Computational Linguistics, 2017. pp. 92-101
@inproceedings{79a2d8fcda744f579daa98f601d4f02b,
title = "Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media",
abstract = "Consumer spending is a vital macroeconomic indicator. In this paper we presenta novel method for predicting future consumer spending from social media data. In contrast to previous work that largely relied on sentiment analysis, the proposed method models consumer spending from purchase intentions found on social media. Our experiments with time series analysis models and machine-learning regression models reveal utility of this data for making short-term forecasts of consumer spending: for three- and seven-day horizons, prediction variables derived from social media help to improve forecast accuracy by 11{\%} to 18{\%} for all the three models, in comparison to models that used only autoregressive predictors.",
author = "Viktor Pekar and Jane Binner",
note = "{\circledC} 2017 The Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.",
year = "2017",
month = "9",
day = "8",
doi = "10.18653/v1/W17-52",
language = "English",
pages = "92--101",
booktitle = "Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
publisher = "Association for Computational Linguistics",

}

Pekar, V & Binner, J 2017, Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media. in Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Association for Computational Linguistics, Copenhagen, Denmark, pp. 92-101. https://doi.org/10.18653/v1/W17-52

Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media. / Pekar, Viktor; Binner, Jane.

Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Copenhagen, Denmark : Association for Computational Linguistics, 2017. p. 92-101.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media

AU - Pekar, Viktor

AU - Binner, Jane

N1 - © 2017 The Association for Computational Linguistics. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License.

PY - 2017/9/8

Y1 - 2017/9/8

N2 - Consumer spending is a vital macroeconomic indicator. In this paper we presenta novel method for predicting future consumer spending from social media data. In contrast to previous work that largely relied on sentiment analysis, the proposed method models consumer spending from purchase intentions found on social media. Our experiments with time series analysis models and machine-learning regression models reveal utility of this data for making short-term forecasts of consumer spending: for three- and seven-day horizons, prediction variables derived from social media help to improve forecast accuracy by 11% to 18% for all the three models, in comparison to models that used only autoregressive predictors.

AB - Consumer spending is a vital macroeconomic indicator. In this paper we presenta novel method for predicting future consumer spending from social media data. In contrast to previous work that largely relied on sentiment analysis, the proposed method models consumer spending from purchase intentions found on social media. Our experiments with time series analysis models and machine-learning regression models reveal utility of this data for making short-term forecasts of consumer spending: for three- and seven-day horizons, prediction variables derived from social media help to improve forecast accuracy by 11% to 18% for all the three models, in comparison to models that used only autoregressive predictors.

UR - https://www.aclweb.org/anthology/W17-5212

U2 - 10.18653/v1/W17-52

DO - 10.18653/v1/W17-52

M3 - Conference contribution

SP - 92

EP - 101

BT - Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

PB - Association for Computational Linguistics

CY - Copenhagen, Denmark

ER -

Pekar V, Binner J. Forecasting Consumer Spending from Purchase Intentions Expressed on Social Media. In Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. Copenhagen, Denmark: Association for Computational Linguistics. 2017. p. 92-101 https://doi.org/10.18653/v1/W17-52