Content uploaded by Bing Liu
Author content
All content in this area was uploaded by Bing Liu on Nov 24, 2014
Content may be subject to copyright.
A preview of the PDF is not available
Opinion Extraction and Summarization on the Web.
Abstract
The Web has become an excellent source for gathering consumer opinions. There are now numerous Web sources containing such opinions, e.g., product reviews, forums, discussion groups, and blogs. Techniques are now being developed to exploit these sources to help organizations and individuals to gain such important information easily and quickly. In this paper, we first discuss several aspects of the problem in the AI context, and then present some results of our existing work published in KDD-04 and WWW-05.
... A lexicon is the set of opinion words, sentiment phrases and idioms. The lexicon acquisition or expansion is achieved through three techniques: the manual approach, the dictionarybased approach [39]- [43] and the corpus-based approach [37], [44]- [46].The manual approach is not feasible because it is very hard to build a comprehensive lexicon. The dictionary-based approaches use seed opinion words and grow set from an online dictionary like WordNet. ...
... Finding the important aspect of interest for a user is the most important task in sentiment analysis. Feature extraction has been studied in supervised learning approaches [70], [71], frequency based approaches [39], [55], [60], [72]- [75], bootstrapping (from lexicon words or candidate features) [48], [49], [76]- [79], and as a topic modeling approaches [18], [21], [66], [67]. ...
Software review text fragments have considerably valuable information about users experience. It includes a huge set of properties including the software quality. Opinion mining or sentiment analysis is concerned with analyzing textual user judgments. The application of sentiment analysis on software reviews can find a quantitative value that represents software quality. Although many software quality methods are proposed they are considered difficult to customize and many of them are limited. This article investigates the application of opinion mining as an approach to extract software quality properties. We found that the major issues of software reviews mining using sentiment analysis are due to software lifecycle and the diverse users and teams.
... Scientific Opinion Summarization provides a succinct synopsis for scientific documents and helps readers recap salient information and understand the professional discussion. Current work on Opinion Summarization is mostly for product reviews (Hu and Liu, 2006;Amplayo et al., 2021b;Angelidis and Lapata, 2018; and aims at identifying representative and consensus opinions on each aspect of interest under the assumption that the input opinions are noncontroversial. However, summarizing scientific opinions is more controversial and complicated. ...
... The task of opinion summarization is typically decomposed into aspect extraction, polarity identification, and summary generation (Hu and Liu, 2006). The lack of parallel data in review opinion summaries limits the scope of most methods into the few-shot abstractive setting (Brazinskas et al., 2020a(Brazinskas et al., , 2022 or unsupervised extractive setting (Angelidis and Lapata, 2018;Chowdhury et al., 2022), where the aspects and sentiments from the input reviews are collected, selected, and rearranged into the output meta-reviews. ...
Opinions in the scientific domain can be divergent, leading to controversy or consensus among reviewers. However, current opinion summarization datasets mostly focus on product review domains, which do not account for this variability under the assumption that the input opinions are non-controversial. To address this gap, we propose the task of scientific opinion summarization, where research paper reviews are synthesized into meta-reviews. To facilitate this task, we introduce a new ORSUM dataset covering 10,989 paper meta-reviews and 40,903 paper reviews from 39 conferences. Furthermore, we propose the Checklist-guided Iterative Introspection (CGI) approach, which breaks down the task into several stages and iteratively refines the summary under the guidance of questions from a checklist. We conclude that (1) human-written summaries are not always reliable since many do not follow the guideline, and (2) the combination of task decomposition and iterative self-refinement shows promising discussion involvement ability and can be applied to other complex text generation using black-box LLM.
... Communications of this type, which pervade social media, have provided fertile ground for the growth and success of opinion mining in NLP. Opinion mining is concerned with the computational processing of stances and emotions targeted towards entities, events, and their properties (Hu and Liu 2006). The same sort of information is the bulk of study for the targeted group in our hierarchy. ...
Humans are naturally endowed with the ability to write in a particular style. They can, for instance, rephrase a formal letter in an informal way, convey a literal message with the use of figures of speech or edit a novel by mimicking the style of some well-known authors. Automating this form of creativity constitutes the goal of style transfer. As a natural language generation task, style transfer aims at rewriting existing texts, and specifically, it creates paraphrases that exhibit some desired stylistic attributes. From a practical perspective, it envisions beneficial applications, like chatbots that modulate their communicative style to appear empathetic, or systems that automatically simplify technical articles for a non-expert audience.
Several style-aware paraphrasing methods have attempted to tackle style transfer. A handful of surveys give a methodological overview of the field, but they do not support researchers to focus on specific styles. With this paper, we aim at providing a comprehensive discussion of the styles that have received attention in the transfer task. We organize them in a hierarchy, highlighting the challenges for the definition of each of them and pointing out gaps in the current research landscape. The hierarchy comprises two main groups. One encompasses styles that people modulate arbitrarily, along the lines of registers and genres. The other group corresponds to unintentionally expressed styles, due to an author’s personal characteristics. Hence, our review shows how these groups relate to one another and where specific styles, including some that have not yet been explored, belong in the hierarchy. Moreover, we summarize the methods employed for different stylistic families, hinting researchers towards those that would be the most fitting for future research.
... Apart from traditional document summarization methods, a number of algorithms (Hu and Liu 2004;Inouye and Kalita 2011;Hu and Liu 2006;Yan et al. 2011;Shou et al. 2013;Chen et al. 2015) are designed to summarize the massive collection of tweets, reviews and news. However, to the best of our knowledge, there is no prior work on summarization of time-sync video comments from the new interactive feature on many video sharing websites. ...
With the rapid growth of online sharing media, we are facing a huge collection of videos. In the meantime, due to the volume and complexity of video data, it can be tedious and time consuming to index or annotate videos. In this paper, we propose to generate temporal descriptions of videos by exploiting the information of crowdsourced time-sync comments which are receiving increasing popularity on many video sharing websites. In this framework, representative and interesting comments of a video are selected and highlighted along the timeline, which provide an informative description of the video in a time-sync manner. The challenge of the proposed application comes from the extremely informal and noisy nature of the comments, which are usually short sentences and on very different topics. To resolve these issues, we propose a novel temporal summarization model based on the data reconstruction principle, where representative comments are selected in order to best reconstruct the original corpus at the text level as well as the topic level while incorporating the temporal correlations of the comments. Experimental results on real-world data demonstrate the effectiveness of the proposed framework and justify the idea of exploiting crowdsourced time-sync comments as a bridge to describe videos.
... The FBSA approach to sentiment computation requires a sentimentannotated corpus, annotated at the level of tokens. (Hu and Liu 2006). This corpus provides a diversity of sentiment-related information and determines the reliability of the analysis. ...
This paper aims to construct a linguistic resource of Korean Multiword Expressions for Feature-Based Sentiment Analysis (FBSA): DECO-MWE. Dealing with multiword expressions (MWEs) has been a critical issue in FBSA since many constructs reveal lexical idiosyncrasy. To construct linguistic resources of sentiment MWEs efficiently, we utilize the Local Grammar Graph (LGG) methodology: DECO-MWE is formalized as a Finite-State Transducer that represents lexical-syntactic restrictions on MWEs. In this study, we built a corpus of cosmetics review texts, which show particularly frequent occurrences of MWEs. Based on an empirical examination of the corpus, four types of MWEs have been discerned. The DECO-MWE thus covers the following four categories: Standard Polarity MWEs (SMWEs), Domain-Dependent Polarity MWEs (DMWEs), Compound Named Entity MWEs (EMWEs) and Compound Feature MWEs (FMWEs). The retrieval performance of the DECO-MWE shows 0.806 f-measure in the test corpus. This study brings a twofold outcome: first, a sizeable general-purpose polarity MWE lexicon, which may be broadly used in FBSA; second, a finite-state methodology adopted in this study to treat domain-dependent MWEs such as idiosyncratic polarity expressions, named entity expressions or feature expressions, and which may be reused in describing linguistic properties of other corpus domains.
... They applaud, disapprove, communicate values, and as social media allow to access loads of communications of this type, it has provided fertile ground for the growth and success of opinion mining in NLP. Opinion mining is concerned with the computational processing of stances and emotions which are targeted towards entities, events and their properties (Hu and Liu 2006). The same information is the bulk of study in the targeted group of our hierarchy. ...
Humans are naturally endowed with the ability to write in a particular style. They can, for instance, rephrase a formal letter in an informal way, convey a literal message with the use of figures of speech, edit a novel mimicking the style of some well-known authors. Automating this form of creativity constitutes the goal of style transfer. As a natural language generation task, style transfer aims at re-writing existing texts, and specifically, it creates paraphrases that exhibit some desired stylistic attributes. From a practical perspective, it envisions beneficial applications, like chat-bots that modulate their communicative style to appear empathetic, or systems that automatically simplify technical articles for a non-expert audience. Style transfer has been dedicated several style-aware paraphrasing methods. A handful of surveys give a methodological overview of the field, but they do not support researchers to focus on specific styles. With this paper, we aim at providing a comprehensive discussion of the styles that have received attention in the transfer task. We organize them into a hierarchy, highlighting the challenges for the definition of each of them, and pointing out gaps in the current research landscape. The hierarchy comprises two main groups. One encompasses styles that people modulate arbitrarily, along the lines of registers and genres. The other group corresponds to unintentionally expressed styles, due to an author's personal characteristics. Hence, our review shows how the groups relate to one another, and where specific styles, including some that have never been explored, belong in the hierarchy. Moreover, we summarize the methods employed for different stylistic families, hinting researchers towards those that would be the most fitting for future research.
Most of the health organizations provide an array of medical services and request their beneficiaries to provide their experience's in the form of opinion/reviews for which they are associated. Doctors of national and international repute have hundreds and even thousands of reviews authored by the health consumers around the globe. For an individual it is difficult and time consuming process to look all the reviews before taking an appropriate decision. Thus it is necessary to summarize the reviews to make an individual to take prompt decision. For a doctor it is also difficult to keep track of patient's reviews given by the patients in different time intervals, but he may have the summary of his entire patient's reviews to understand what is the best can be done to the patient's community. This research paper aims to mine and summarize the medical reviews authored by the health consumers. This article is performed by summarization of text in three steps, the first step is to identify the health features that have been commented by health consumers, the next one is to identify opinions of each review sentence and deciding whether each opinion sentence is positive or negative and finally summarizing the results. Keywords-national and international repute, medical reviews, health consumer, summarization of text and health features
Depuis l’apparition du terme “e-réputation” dans un article scientifique en 2000 (McDonald et Slawson), force est de constater que, l’étude de ce phénomène est encore à l’état embryonnaire, et de nombreuses pistes restent à être explorées, notamment sur les approches mobilisées afin de le mesurer, de l’évaluer. L’objectif principal de nos travaux de recherche est de déterminer si les professionnels de la réputation numérique s’appuient, peu ou prou, dans leurs offres de mesure, sur des modèles académiques ou conceptuels. Déterminer un éventuel rapport entre les deux approches suppose un questionnement à la fois empirique et théorique. Sur le plan théorique, à partir d’une taxonomie des modèles conceptuels de la réputation, nous nous intéresserons aux dimensions structurelles et méthodologiques mises en œuvre dans le processus d’évaluation. Ces dimensions nous permettront d’identifier des catégories de modèles. L’approche empirique vise, sur la base d’entrevues réalisées auprès de professionnels, à circonscrire le marché de l’e-réputation en termes d’acteurs, mais aussi et surtout de prestations de service. Ces dernières, et plus particulièrement les méthodes de mesure déployées, feront par la suite l’objet d’une mise en regard avec les modèles théoriques issus de la littérature scientifique essentiellement anglo-saxonne.
This paper presents a simple unsupervised learning algorithm for classifying reviews as recommended (thumbs up) or not rec- ommended (thumbs down). The classifi- cation of a review is predicted by the average semantic orientation of the phrases in the review that contain adjec- tives or adverbs. A phrase has a positive semantic orientation when it has good as- sociations (e.g., "subtle nuances") and a negative semantic orientation when it has bad associations (e.g., "very cavalier"). In this paper, the semantic orientation of a phrase is calculated as the mutual infor- mation between the given phrase and the word "excellent" minus the mutual information between the given phrase and the word "poor". A review is classified as recommended if the average semantic ori- entation of its phrases is positive. The al- gorithm achieves an average accuracy of 74% when evaluated on 410 reviews from Epinions, sampled from four different domains (reviews of automobiles, banks, movies, and travel destinations). The ac- curacy ranges from 84% for automobile reviews to 66% for movie reviews.
Identifying sentiments (the affective parts of opinions) is a challenging problem. We present a system that, given a topic, automatically finds the people who hold opinions about that topic and the sentiment of each opinion. The system contains a module for determining word sentiment and another for combining sentiments within a sentence. We experiment with various models of classifying and combining sentiment at word and sentence levels, with promising results.
Merchants selling products on the Web often ask their customers to review the products that they have purchased and the associated services. As e-commerce is becoming more and more popular, the number of customer reviews that a product receives grows rapidly. For a popular product, the number of reviews can be in hundreds or even thousands. This makes it difficult for a potential customer to read them to make an informed decision on whether to purchase the product. It also makes it difficult for the manufacturer of the product to keep track and to manage customer opinions. For the manufacturer, there are additional difficulties because many merchant sites may sell the same product and the manufacturer normally produces many kinds of products. In this research, we aim to mine and to summarize all the customer reviews of a product. This summarization task is different from traditional text summarization because we only mine the features of the product on which the customers have expressed their opinions and whether the opinions are positive or negative. We do not summarize the reviews by selecting a subset or rewrite some of the original sentences from the reviews to capture the main points as in the classic text summarization. Our task is performed in three steps: (1) mining product features that have been commented on by customers; (2) identifying opinion sentences in each review and deciding whether each opinion sentence is positive or negative; (3) summarizing the results. This paper proposes several novel techniques to perform these tasks. Our experimental results using reviews of a number of products sold online demonstrate the effectiveness of the techniques.
The abstract for this document is available on CSA Illumina.To view the Abstract, click the Abstract button above the document title.
We present a methodology for summarization of news about current events in the form of briefings that include appropriate background (historical) information. The system that we developed, SUMMONS, uses the output of systems developed for the DARPA Message Understanding Conferences to generate summaries of multiple documents on the same or related events, presenting similarities and differences, contradictions, and generalizations among sources of information. We describe the various components of the system, showing how information from multiple articles is combined, organized into a paragraph, and finally, realized as English sentences. A feature of our work is the extraction of descriptions of entities such as people and places for reuse to enhance a briefing.