The use of twitter data to improve small area estimates of households' share of food consumption expenditure in Italy

The use of big data in many socio-economic studies has received a growing interest in the last few years. In this work we use an index computed using emotional data coming from Twitter as auxiliary variable in a small area model to estimate Italian households' share of food consumption expenditure (the proportion of food consumption expenditure on the total consumption expenditure) at provincial level. We show that the index based on Twitter has a potential in predicting our target variable, and that using the index as auxiliary variable in the small area working model results in a further reduction of the estimated mean squared error with respect to the same estimator that does not make use of this index.