Consumers today are heavily dependent on online reviews to make informed choices about what to buy. In fact, studies show that as many as 90 percent of consumers read online reviews before making financial decisions, and nearly 70 percent trust these opinions.
Given their importance, how do you tell if the reviews are from genuine customers?
Subodha Kumar, director of the Center for Data Analytics and professor of Marketing and Supply Chain Management at the Fox School, developed an approach to detect fake reviewers on online digital platforms. In his paper published in the Journal of Management Information Systems, Kumar proposes an algorithm that analyzes the behavior of reviewers on a set of key features to help differentiate between the real and the fake.
“A user who reads a negative review of a restaurant is likely to trust the message, even though it was written by a stranger,” Kumar says. “One convincing review can often persuade consumers to shift their brand loyalty or drive several extra miles to try a new sandwich shop.”
This gives firms a strong incentive to influence their online review ratings. “Business owners inject their public ratings with a positive bias,” says Kumar. “They use fake accounts or paid reviewers to either promote their offering or strategically denounce competitors’ products.”
In studying a dataset from Yelp, a popular restaurant review platform, Kumar observed a striking difference in the way spammers interact on online platforms. “Even though individual reviews by a spammer may look genuine, collectively we can capture anomalies in the review patterns,” Kumar says, “In fact, they are remarkably skewed.”
By analyzing this pattern of behaviors, Kumar’s approach to detecting review manipulation can not only improve the experience of consumers across industries but also increase the credibility of reviewing platforms like Yelp.
Kumar considers six distinct features of every review in the data set:
- Review gap: Spammers are usually not longtime members of a site, unlike genuine reviewers who use their accounts from time to time to post reviews. Thus, if reviews are posted over a relatively long timeframe, it suggests normal activity. But when all reviews are posted within a short burst, it indicates suspicious behavior.
- Review count: Paid users generally generate more reviews than unpaid users. In other cases to avoid being detected or blacklisted, a spammer could post very few reviews from one account and create a new account.
- Rating entropy: Spammers mostly post extreme reviews since their goal is either to artificially improve a particular company’s rating or to bring a bad reputation to its competitors. This results in high entropy—or drastic randomness—in fake users’ ratings.
- Rating deviation: Spammers are likely to deviate from the general rating consensus. If genuine users fairly outnumber spammers, it is easy to detect instances where a user’s rating deviates greatly from the average ratings from other users.
- Timing of review: One strategy spammers may use is to post extremely early after a restaurant’s opening in order to maximize the impact of their review. Early reviews can greatly impact a consumers’ sentiment on a product and, in turn, impact sales.
- User tenure: Fake reviewers tend to have short-lived accounts characterized by a relatively large number of reviews and handles, usernames or aliases designed to avoid detection.
After considering these variables individually, the algorithm then looks into the way the variables interact with each other. It employs techniques like supervised machine learning and accounts for the overall review behavior of a user to provide a robust and accurate analysis.
Kumar’s methodology can also be deployed to post the information of the spammers in real-time. Digital platforms like Yelp could develop a spam score using these key features for each reviewer and share it with business owners and consumers, who can subsequently be tagged or filtered.
“The issue of opinion spamming in online reviews is not going away and detecting the perpetrators is not easy,” says Kumar. But developments in approaches like these, he says, “offer great insights to businesses, allowing them to create more effective marketing strategies based on the sheer volume of genuine, user-contributed consumer reviews.”
A professor from Temple University’s Fox School of Business has been named one of the most-productive authors in marketing research in the world.
Dr. Xueming Luo is recognized in two separate lists within the American Marketing Association (AMA) 2016 Marketing Research Productivity lists. He ranks No. 11 globally for research publications in the two premier journals – the Journal of Marketing (JM) and the Journal of Marketing Research (JMR). Also, he ranks No. 28 in the world for publications to the four premier marketing journals – JM, JMR, the Journal of Consumer Research, and Marketing Science.
Published in January 2017, the AMA lists acknowledge the top individual contributors to the world’s premier marketing journals over a 10-year period, from 2007-2016.
“I am humbled and honored to have been recognized by the American Marketing Association,” said Luo, the Charles Gilliland Distinguished Chair Professor of Marketing. “These four premier journals together are the most influential and hold the highest standards in the entire marketing discipline, and across all streams of research in consumer behavior and quantitative marketing.”
Luo’s research centers on mobile consumer analytics; big data marketing strategies; and social media, marketing models with machine learning, and networks. He serves as founder and director of the Fox School’s Global Center on Big Data and Mobile Analytics, a leading center in the cross-disciplinary domain of big data for business strategies and consumer insights.
He previously has been ranked No. 1 nationally among preeminent scholars in his discipline regarding citations in the top-five marketing journals, from 2006-2010. And from 2011-2015, he ranked among the 20 most-productive authors of research in Premier AMA journals.
Five of the Fox School’s nine academic departments are nationally ranked for overall research productivity. In the 2015-16 academic year, Fox faculty published more than 40 A journal publications, secured more than $5 million in grant funding, and increased new grant funding by nearly $1 million.
It’s on a crowded subway train that the next big thing in mobile analytics has emerged. New research by a professor from the Fox School of Business shows an upswing in mobile purchases as consumers turn to their smartphones to disengage from the hassle of a packed train.
For the study’s coauthor, Dr. Xueming Luo, Charles Gilliland Chair Professor of Marketing, Strategic Management, and Information Systems at Fox, the results are both impactful and surprising.
“Crowded environments are oftentimes noisy and annoying,” said Luo. “We expected them to turn customers off to such purchases. That wasn’t the case.”
Luo’s study, which has been cited by the United Kingdom’s Daily Mail among other media outlets, was coauthored by Emory University’s Dr. Michelle Andrews, a Fox PhD alumna; Sichuan University’s Dr. Zheng Fang; and New York University’s Dr. Anindya Ghose.
The study partnered with a cell phone service provider that over several days sent randomly selected subway riders in a large Asian city mobile ads for digital services such as video-streaming. The study found that smartphone users trapped in densely packed trains were about two times more likely to opt to buy the promoted mobile services than those in non-crowded trains.
Though crowding is subjective, the study focused on participants with at least five or more people positioned within 10 square feet. In order to determine that crowding influenced purchasing behavior, the study examined travelers throughout the day – from rush hour business people to lull-hour, non-business casual travelers.
“It’s about being around strangers and having a fear of social awkwardness,” said Luo, and the Founder and Director of Temple University’s Global Center for Big Data in Mobile Analytics. “To avoid eye contact we reach for our phones. This happens in elevators, too. Your smartphone saves you from awkward social moments.”
Using smartphones as a coping strategy, consumers block out external social interactions and allowed marketers and advertisers to have their full attention, Luo said. And in order to maintain that attention, he said, marketers rely on creativity in cultivating consumer staying power in a market consumed by its ability to flick, click, and dismiss anything that bores them.
Understanding consumer attention spans is a part of Luo’s larger research in mobile analytics. The most effective way to engage consumers, he said, is to offer personalized incentives – from discounts to ads that appeal to a consumer’s proximity to a business. Sending out targeted geographic and temporal advertisements is well-received in instances in which consumers are annoyed by noise or crowding on their commutes.
“Cutting–edge marketing is all about delivering the right message at the right place and right moment to make an impact,” Luo said. “Smartphone technology can be leveraged to attain that, especially in a crowded subway train.”
There’s a crucial strategy in online advertising that could revolutionize the way marketing agencies target online consumers, according to Fox School of Business researcher.
Dr. Xueming Luo studied how the strategy of competitor-poaching in online advertising influences consumer behavior. His most-recent publication on the topic was named Best Track Paper in Social Media & Digital Marketing at the 2015 American Marketing Association Winter Educator Conference Feb. 14 in San Antonio, Texas. It also received the conference’s honorable-mention distinction among all submissions.
Competitor-poaching in online advertising is responsible for why consumers can search the term “iPhone” using Google’s search engine, and corresponding ads for the Samsung Galaxy, Apple’s closest competitor, will appear, said Luo, Professor of Marketing, Strategy, and Management Information Systems. In his research, Luo uncovered that this strategy results in “clicks wasted,” as consumers glance over the competitor’s ads while remaining loyal to their initial preferences.
“It’s a double-edged sword,” Luo said. “You can increase the impression of the competitor’s brand, but you cannot get consumers to purchase the poaching brand.”
This effect is partly seen because online consumers often develop specific brand loyalties by word of mouth or from reviews that sites like Amazon and Google provide, he said. Firms, Luo found, seek to continually build brand equity and increase positive socialization around their products in order to thwart attempts at online poaching.
“Online poaching impresses non-loyal customers, but fails to get more sales conversion from customers who have high loyalty to the brand under attack” Luo said.
Asking a consumer why they want or prefer a certain product or brand, and how price influences their decisions, can help clarify what incentivizes shoppers, Luo said. Marketing agencies should then target their competitor’s keywords with advertisements that include discounts, he suggested, to capture consumer curiosity.
“To switch consumers from a brand, you need a deeper incentive, such as a 30-percent discount,” Luo said. “If you do this the wrong way, you’ll waste your money. That method can only engender clicks, but not sales conversion.”
This research, Luo said, is a part of his greater interest in how online marketing interweaves big-data analytics, mobile strategies, and consumer insights. As founder of the Global Center on Big Data in Mobile Analytics, which is housed at the Fox School, Luo is interested in investigating how big data gleaned from search engines reveal varying patterns in the evolving sphere of online ads and mobile targeting.
“This is a great way to outsmart competitors and connect customers for superior company performance,” Luo said.