Word Salad: Relating Food Prices and Descriptions

Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1357–1367, Jeju Island, Korea, 12–14 July 2012. c⃝2012 Association for Computational Linguistics Word Salad: Relating Food Prices and Descriptions Victor Chahuneau Kevin Gimpel Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA {vchahune,kgimpel}@cs.cmu.edu Bryan R. Routledge Tepper School of Business Carnegie Mellon University Pittsburgh, PA 15213, USA routledge@cmu.edu Lily Scherlis Phillips Academy Andover, MA 01810, USA lily.scherlis@gmail.com Noah A. Smith Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA nasmith@cs.cmu.edu Abstract We investigate the use of language in food writing, specifically on restaurant menus and in customer reviews. Our approach is to build predictive models of concrete external vari- ables, such as restaurant menu prices. We make use of a dataset of menus and customer reviews for thousands of restaurants in several U.S. cities. By focusing on prediction tasks and doing our analysis at scale, our method- ology allows quantitative, objective measure- ments of the words and phrases used to de- scribe food in restaurants. We also explore interactions in language use between menu prices and sentiment as expressed in user re- views. 1 Introduction What words might a menu writer use to justify the high price of a steak? How does describing an item as chargrilled vs. charbroiled affect its price? When a customer writes an unfavorable review of a restau- rant, how is her word choice affected by the restau- rant’s prices? In this paper, we explore questions like these that relate restaurant menus, prices, and customer sentiment. Our goal is to understand how language is used in the food domain, and we di- rect our investigation using external variables such as restaurant menu prices. We build on a thread of NLP research that seeks linguistic understanding by predicting real-world quantities from text data. Recent examples include prediction of stock volatility (Kogan et al., 2009) and movie revenues (Joshi et al., 2010). There, pre- diction tasks were used for quantitative evaluation and objective model comparison, while analysis of learned models gave insight about the social process behind the data. We echo this pattern here as we turn our atten- tion to language use on restaurant menus and in user restaurant reviews. We use data from a large cor- pus of restaurant menus and reviews crawled from the web and formulate several prediction tasks. In addition to predicting menu prices, we also consider predicting sentiment along with price. The relationship between language and senti- ment is an active area of investigation (Pang and Lee, 2008). Much of this research has focused on customer-written reviews of goods and services, and perspectives have been gained on how sentiment is expressed in this type of informal text. In addition to sentiment, however, other variables are reflected in a reviewer’s choice of words, such as the price of the item under consideration. In this paper, we take a step toward joint modeling of multiple variables in review text, exploring connections between price …

Content truncated to 500 words