Myle Ott

Multi-aspect Sentiment Analysis with Topic Models

We investigate the efficacy of topic model based approaches to two multi-aspect sentiment analysis tasks: multi-aspect sentence labeling and multi-aspect rating prediction. For sentence labeling, we propose a weakly-supervised approach that utilizes only minimal prior knowledge -- in the form of seed words -- to enforce a direct correspondence between topics and aspects. This correspondence is used to label sentences with performance that approaches a fully supervised baseline. For multi-aspect rating prediction, we find that overall ratings can be used in conjunction with our sentence labelings to achieve reasonable performance compared to a fully supervised baseline. When gold-standard aspect-ratings are available, we find that topic model based features can be used to improve unsophisticated supervised baseline performance, in agreement with previous multi-aspect rating prediction work. This improvement is diminished, however, when topic model features are paired with a more competitive supervised baseline -- a finding not acknowledged in previous work.

Towards a General Rule for Identifying Deceptive Opinion Spam

Consumers’ purchase decisions are increasingly influenced by user-generated online reviews. Accordingly, there has been growing concern about the potential for posting deceptive opinion spam— fictitious reviews that have been deliberately written to sound authentic, to deceive the reader. In this paper, we explore generalized approaches for identifying online deceptive opinion spam based on a new gold standard dataset, which is comprised of data from three different domains (i.e. Hotel, Restaurant, Doctor), each of which contains three types of reviews, i.e. customer generated truthful reviews, Turker generated deceptive reviews and employee (domain-expert) generated deceptive reviews. Our approach tries to capture the general difference of language usage between deceptive and truthful reviews, which we hope will help customers when making purchase decisions and review portal operators, such as TripAdvisor or Yelp, investigate possible fraudulent activity on their sites. 1

Linguistic Models of Deceptive Opinion Spam

of the talk Consumers increasingly inform their purchase decisions with opinions and other information found on the Web. Unfortunately, the ease of posting content online, potentially anonymously, combined with the publics trust and growing reliance on this content, creates opportunities and incentives for abuse. This is especially worrisome in the case of online reviews of products and services, where businesses may feel pressure to post deceptive opinion spam---fictitious reviews disguised to look like authentic customer reviews. In recent years, several approaches have been proposed to identify deceptive opinion spam based on linguistic cues in a reviews text. In this talk I will summarize a few of these approaches. I will additionally discuss some of the challenges researchers face when studying this problem, including the difficulty of obtaining labeled data, uncertainties surrounding the prevalence of deception, and how linguistic cues to deceptive opinion spam vary with the texts sentiment (e.g., 5-star vs 1and 2star reviews), domain (e.g., hotel vs. restaurant reviews) and the domain expertise of the author (e.g., crowdsourced vs. employee-written deceptive opinion spam).