Abstract

A typical trade-off in decision-making is between the cost of acquiring information and the decline in decision quality caused by insufficient information. Consumers regularly face this trade-off in purchase decisions. Online product/service reviews serve as sources of product/service related information. Meanwhile, modern technology has led to an abundance of such content, which makes it prohibitively costly (if possible at all) to exhaust all available information. Consumers need to decide what subset of available information to use. Star ratings are excellent cues for this decision as they provide a quick indication of the tone of a review. However there are cases where such ratings are not available or detailed enough. Sentiment analysis - text analytic techniques that automatically detect the polarity of text - can help in these situations with more refined analysis. This study was performed in two interrelated phases. In the first phase the potential impact of Sentiment Scores (sentiment analysis outcomes) was investigated through a comparison between these scores with an already established numerical rating denoted as star ratings in three different domains. The results show that sentiment scores tend to fall into neutral areas and are not able to detect extremes that were reported to be more beneficial for information acquisition purposes. As a result, to use the current sentiment analysis results as a substitute for star ratings, a partial linear filter was applied to sentiment analysis results in a way to highlight the subtle differences away from the "neutral zone". In the second phase, the impact of the extended version of sentiment scores on decision outcomes was examined through a controlled experiment. The examined decision was a purchase decision and the information provided was pages of reviews annotated with extended sentiment scores on each paragraph. Human subjects were used in the experiment and controlled data gathering sessions was designed. Results suggest that female consumers may use sentiment scores on review documents without other comparison aids to increase their confidence level in their purchase decisions.

Highlights

  • The results show that sentiment scores tend to fall into neutral areas and are not able to detect extremes that were reported to be more beneficial for information acquisition purposes

  • The results show that the sentiment analysis has limited ability to detect extreme ratings explicitly assigned by reviewers

  • If that is the case, to be compatible with star ratings, sentiment analysis techniques need to be more sensitive to the subtleties in natural language expressions

Read more

Summary

Introduction

The rapid increase in the volume of review information available as well as the substantial amount of user generated reviews, creates the problem of information overload To mitigate this problem, consumers use decision and comparison aids [34] and numerical content ratings (such as star ratings) [35] to conserve cognitive resources and reduce energy expenditure to acquire information, and to ease or improve the purchase decision process [26]. Sentiment analysis technology has been claimed to help users to make wiser decisions [39] We believe that this can be due to the fact that sentiment evaluations on a piece of document can be used as a cue for information acquisition purposes and for more effective and efficient decision outcome. We will assess this claim by investigating the impact of one particular sentiment analysis outcome-sentiment scores- on a specific decision process -purchase decision

Problem specification and research questions
Consumer purchase decisions
Sentiment Analysis Technology
Sentiment Analysis Applications As stated above, Sentiment
Methodology
Data selection process We first selected four different products from the
Sentiment Analysis Tool
Analysis of data We conducted sentiment analysis on each comment for each dataset using Lexalytics
Product 4 Data Set
Discussion and Conclusions
Theoretical background
Information Foraging theory “Information Foraging
Task Technology Fit The ultimate argument of fit models states that Information
Hypothesis and research model development
Research methodology
Experiment design
Measurement Scales
Ethics approval Ryerson
Pilot study
Data collection
Data analysis and results All statistical analyses were done using SPSS software
Coding of variables
Descriptive statistics and frequencies of variables
Limitations
Directions for future research
Background questions
Findings
Decision outcome questions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call