Summarizing Opinion-Related Information for Mobile Devices
Reviews about products and services are abundantly available online. However, gathering information relevant to shoppers involves a significant amount of time reading reviews and weeding out extraneous information. While recent work in multi-document summ
- PDF / 920,344 Bytes
- 29 Pages / 439.37 x 666.14 pts Page_size
- 83 Downloads / 179 Views
Summarizing Opinion-Related Information for Mobile Devices Giuseppe Di Fabbrizio, Amanda J. Stent, and Robert Gaizauskas
Abstract Reviews about products and services are abundantly available online. However, gathering information relevant to shoppers involves a significant amount of time reading reviews and weeding out extraneous information. While recent work in multi-document summarization has attempted to some degree to address this challenge, many questions about extracting and aggregating opinions remain unanswered. This chapter demonstrates a novel approach to review summarization, using three techniques: (1) graphical summarization; (2) review summarization; and (3) a hybrid approach, which combines abstractive and extractive summarization methods, to extract relevant opinions and relative ratings from text documents. All three methods allow a consistent approach to preserve the overall opinion distribution that is expressed in the original reviews.
G. Di Fabbrizio (*) Lead Member of Technical Staff, AT&T Labs – Research, 180 Park Avenue – Building 103, Florham Park, NJ, USA e-mail: [email protected] A.J. Stent Principal Member of Technical Staff, AT&T Labs – Research, 180 Park Avenue – Building 103, Florham Park, NJ 07932, USA e-mail: [email protected] R. Gaizauskas Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK e-mail: [email protected] A. Neustein and J.A. Markowitz (eds.), Mobile Speech and Advanced Natural Language Solutions, DOI 10.1007/978-1-4614-6018-3_11, © Springer Science+Business Media New York 2013
G. Di Fabbrizio et al.
Introduction The last 5 years have seen transformational advances in the use of advanced networked mobile devices, enabling users to merge their online and offline lives as never before. One of the daily life tasks that is most illustrative of this transformation is purchasing. Consumers on-the-go increasingly rely on internet search to find services and products, and on online reviews to select from among them. The actual purchase of the selected service or product may take place online or at a bricks-andmortar location. A study conducted by The E-tailing Group1 describes an emerging breed of shopper, the social researcher, who seeks out opinions expressed by online peers before making buying decisions. According to this research, 78 % of the 1,200 sampled consumers spent more than 10 min reading reviews online. Additionally, 65 % meet the definition of social researchers and 86 % of social researchers rated online reviews and product ratings an extremely or very important factor influencing their buying decisions. Another study2 carried out by comScore and The Kelsey Group revealed that a significant portion of offline product and service sales (24 % of the 2,000 interviewed users) are made after consulting online reviews while three quarters of consumers who consulted online reviews reported that the reviews had a significant influence on their purchase. Retailers and servi
An Attention-Information-Based Spatial Adaptation Framework for Browsing Videos via Mobile Devices
119 110 1MB