Sentiment Analysis in TripAdvisor Valdivia, Ana; Luzon, M. Victoria; Herrera, Francisco
IEEE intelligent systems,
2017, Volume:
32, Issue:
4
Journal Article
Peer reviewed
Web platforms such as TripAdvisor allow tourists to describe their experiences with hotels, restaurants, and other tourist attractions. This article proposes TripAdvisor as a source of data for ...sentiment analysis tasks. The authors develop an analysis for studying the matching between users' sentiments and automatic sentiment-detection algorithms. They also discuss some of the challenges regarding sentiment analysis and TripAdvisor.
Federated Learning is a distributed machine learning paradigm vulnerable to different kind of adversarial attacks, since its distributed nature and the inaccessibility of the data by the central ...server. In this work, we focus on model-poisoning backdoor attacks, because they are characterized by their stealth and effectiveness. We claim that the model updates of the clients of a federated learning setting follow a Gaussian distribution, and those ones with an outlier behavior in that distribution are likely to be adversarial clients. We propose a new federated aggregation operator called Robust Filtering of one-dimensional Outliers (RFOut-1d), which works as a resilient defensive mechanism to model-poisoning backdoor attacks. RFOut-1d is based on an univariate outlier detection method that filters out the model updates of the adversarial clients. The results on three federated image classification dataset show that RFOut-1d dissipates the impact of the backdoor attacks to almost nullifying them throughout all the learning rounds, as well as it keeps the performance of the federated learning model and it outperforms that state-of-the-art defenses against backdoor attacks.
Opinion summarisation is concerned with generating structured summaries of multiple opinions in order to provide insightful knowledge to end users. We present the Aspect Discovery for OPinion ...Summarisation (ADOPS) methodology, which is aimed at generating explainable and structured opinion summaries. ADOPS is built upon aspect-based sentiment analysis methods based on deep learning and Subgroup Discovery techniques. The resultant opinion summaries are presented as interesting rules, which summarise in explainable terms for humans the state of the opinion about the aspects of a specific entity. We annotate and release a new dataset of opinions about a single entity on the restaurant review domain for assessing the ADOPS methodology, and we call it ORCo. The results show that ADOPS is able to generate interesting rules with high values of support and confidence, which provide explainable and insightful knowledge about the state of the opinion of a certain entity.
•We present a novel methodology for aspect-based opinion summarisation.•Our methodology combines deep learning and subgroup discovery methods.•We categorise the aspects of restaurant reviews and classify their opinion values.•The summaries are presented in explainable terms for humans as interesting rules.•We release a new dataset for assessing opinion summarisation models.
•Weighted aggregation models are proposed for sentiment classification.•There is a low consensus for detecting neutral polarities.•Neutrality is key for improving classification results. It is ...detected by weighted aggregation models.•Aggregation models outperforms single models in sentiment classification.
Recently, interest in sentiment analysis has grown exponentially. Many studies have developed a wide variety of algorithms capable of classifying texts according to the sentiment conveyed in them. Such sentiment is usually expressed as positive, neutral or negative. However, neutral reviews are often ignored in many sentiment analysis problems because of their ambiguity and lack of information. In this paper, we propose to empower neutrality by characterizing the boundary between positive and negative reviews, with the goal of improving the model’s performance. We apply different sentiment analysis methods to different corpora extracting their sentiment and, hence, detecting neutral reviews by consensus to filter them, i.e., taking into account different models based on weighted aggregation. We finally compare classification performance on single and aggregated models. The results clearly show that aggregation methods outperform single models in most cases, which led us to conclude that neutrality is key for distinguishing between positive and negative and, then, for improving sentiment classification.
TripAdvisor is an opinion source frequently used in Sentiment Analysis. On this social network, users explain their experiences in hotels, restaurants or touristic attractions. They write texts of ...200 character minimum and score the overall of their review with a numeric scale that ranks from 1 (Terrible) to 5 (Excellent). In this work, we aim that this score, which we define as the User Polarity, may not be representative of the sentiment of all the sentences that make up the opinion. We analyze opinions from six Italian and Spanish monument reviews and detect that there exist inconsistencies between the User Polarity and Sentiment Analysis Methods that automatically extract polarities. The fact is that users tend to rate their visit positively, but in some cases negative sentences and aspects appear, which are detected by these methods. To address these problems, we propose a Polarity Aggregation Model that takes into account both polarities guided by the geometrical mean. We study its performance by extracting aspects of monuments reviews and assigning to them the aggregated polarities. The advantage is that it matches together the sentiment of the context (User Polarity) and the sentiment extracted by a pre-trained method (SAM Polarity). We also show that this score fixes inconsistencies and it may be applied for discovering trustworthy insights from aspects, considering both general and specific context.
Federated learning, as a distributed learning that conducts the training on the local devices without accessing to the training data, is vulnerable to Byzantine poisoning adversarial attacks. We ...argue that the federated learning model has to avoid those kind of adversarial attacks through filtering out the adversarial clients by means of the federated aggregation operator. We propose a dynamic federated aggregation operator that dynamically discards those adversarial clients and allows to prevent the corruption of the global learning model. We assess it as a defense against adversarial attacks deploying a deep learning classification model in a federated learning setting on the Fed-EMNIST Digits, Fashion MNIST and CIFAR-10 image datasets. The results show that the dynamic selection of the clients to aggregate enhances the performance of the global learning model and discards the adversarial and poor (with low quality models) clients.
•We identify Byzantine attacks as a real problem of Federated Learning.•We propose a novel agnostic defense based on a dynamic aggregation operator.•The dynamic aggregation operator is based on the use of an IOWA operator.•The proposed defense outperforms the state-of-the-art defenses on Byzantine attacks.
•Domain adaptation is one of the main challenges of sentiment analysis.•Most polarity detection methods are focused on a specific domain.•Ensemble methods may improve the performance of a set of ...polarity detection methods.•Evolutionary algorithms may find out the right combination of polarity classification methods in an ensemble classifier.•The results show that our claim holds on 13 corpora.
Currently, a plethora of industrial and academic sentiment analysis methods for classifying the opinion polarity of a text are available and ready to use. However, each of those methods have their strengths and weaknesses, due mainly to the approach followed in their design (supervised/unsupervised) or the domain of text used in their development. The weaknesses are usually related to the capacity of generalisation of machine learning algorithms, and the lexical coverage of linguistic resources. Those issues are two of the main causes of one of the challenges of Sentiment Analysis, namely the domain adaptation problem. We argue that the right ensemble of a set of heterogeneous Sentiment Analysis Methods will lessen the domain adaptation problem. Thus, we propose a new methodology for optimising the contribution of a set of off-the-shelf Sentiment Analysis Methods in an ensemble classifier depending on the domain of the input text. The results clearly show that our claim holds.
When data privacy is imposed as a necessity, Federated learning (FL) emerges as a relevant artificial intelligence field for developing machine learning (ML) models in a distributed and decentralized ...environment. FL allows ML models to be trained on local devices without any need for centralized data transfer, thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third parties. This paradigm has gained momentum in the last few years, spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data sources. By virtue of FL, models can be learned from all such distributed data sources while preserving data privacy. The aim of this paper is to provide a practical tutorial on FL, including a short methodology and a systematic analysis of existing software frameworks. Furthermore, our tutorial provides exemplary cases of study from three complementary perspectives: i) Foundations of FL, describing the main components of FL, from key elements to FL categories; ii) Implementation guidelines and exemplary cases of study, by systematically examining the functionalities provided by existing software frameworks for FL deployment, devising a methodology to design a FL scenario, and providing exemplary cases of study with source code for different ML approaches; and iii) Trends, shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL landscape. The ultimate purpose of this work is to establish itself as a referential work for researchers, developers, and data scientists willing to explore the capabilities of FL in practical applications.
The high demand of artificial intelligence services at the edges that also preserve data privacy has pushed the research on novel machine learning paradigms that fit these requirements. Federated ...learning has the ambition to protect data privacy through distributed learning methods that keep the data in its storage silos. Likewise, differential privacy attains to improve the protection of data privacy by measuring the privacy loss in the communication among the elements of federated learning. The prospective matching of federated learning and differential privacy to the challenges of data privacy protection has caused the release of several software tools that support their functionalities, but they lack a unified vision of these techniques, and a methodological workflow that supports their usage. Hence, we present the Sherpa.ai Federated Learning framework that is built upon a holistic view of federated learning and differential privacy. It results from both the study of how to adapt the machine learning paradigm to federated learning, and the definition of methodological guidelines for developing artificial intelligence services based on federated learning and differential privacy. We show how to follow the methodological guidelines with the Sherpa.ai Federated Learning framework by means of a classification and a regression use cases.
•We analyse the most recent federated learning and differential privacy frameworks.•We present Sherpa.ai FL, a unified framework for federated learning and differential privacy.•We discuss the adaptation of machine learning models to federated learning.•We define the guidelines for privacy-preserving artificial intelligence services.