Customer perception of the deceptiveness of online product reviews: A speech act theory perspective

With the presence of fake reviews on e-commerce platforms, the reliability of reviews becomes questionable. The extant literature demonstrates the impact of fake reviews on product sales and proposes several algorithms to prevent fake reviews from being displayed on the platform. However, what has largely remained uninvestigated is how customers perceive reviews present on the e-commerce platform. Based on the speech act theory, we develop a theoretical framework that explains how the linguistic style (both at the word and the structural level) acts as a cue for assessing a reviewer’s (in)sincere intentions. We evaluate the framework on a corpus of 120 online product reviews – each examined by at least 50 customers – using the fractional logit model. Results suggest that the communication style of a speaker reflects his/her intention. Reviews with less contextual embedding, argument structuring, and flattering through non-verbal cues trigger customers towards perceiving a review as deceptive.     

实体-属性抽取的GRU+CRF方法

[目的/意义]研究利用深度学习的循环神经网络GRU结合条件随机场CRF对标注的中文文本序列进行预测,来抽取在线评论文本中的实体-属性。[方法/过程]首先根据设计好的文本序列标注规范,对评论语料分词后进行实体及其属性的命名实体标注,得到单词序列、词性序列和标注序列;然后将单词序列、词性序列转为分布式词向量表示并用于GRU循环神经网络的输入;最后输出层采用条件随机场CRF,输出标签即是实体或属性。[结果/结论]实验结果表明,本文的方法将实体-属性抽取简化为命名实体标注,并利用深度学习的GRU捕获输入数据的上下文语义以及条件随机场CRF获取输出标签的前后关系,比传统的基于规则或一般的机器学习方法具有较大的应用优势。     

基于卷积神经网络的旅游信息关系抽取研究

[目的/意义]在非结构化语料集中抽取知识要素,是实现知识图谱的重要环节,本文探索了应用深度学习中的卷积神经网络（CNN）模型进行旅游领域知识关系抽取方法。[方法/过程]抓取专业旅游网站的相关数据建立语料库,对部分语料进行人工标注作为训练集和测试集,通过Python语言编程实现分词、向量化及CNN模型,进行关系抽取实验。[结果/结论]实验结果表明,应用卷积神经网络对非结构化的旅游文本进行关系抽取时能够取得满意的效果（Precision 0.77,Recall 0.76,F1-measure 0.76）。抽取结果通过人工校对进行优化后,可以为旅游知识图谱构建、领域本体构建等工作奠定基础。     

Word sense disambiguation based on context selection using knowledge-based word similarity

In this paper, we introduce a novel knowledge-based word-sense disambiguation (WSD) system. In particular, the main goal of our research is to find an effective way to filter out unnecessary information by using word similarity. For this, we adopt two methods in our WSD system. First, we propose a novel encoding method for word vector representation by considering the graphical semantic relationships from the lexical knowledge bases, and the word vector representation is utilized to determine the word similarity in our WSD system. Second, we present an effective method for extracting the contextual words from a text for analyzing an ambiguous word based on word similarity. The results demonstrate that the suggested methods significantly enhance the baseline WSD performance in all corpora. In particular, the performance on nouns is similar to those of the state-of-the-art knowledge-based WSD models, and the performance on verbs surpasses that of the existing knowledge-based WSD models.     

Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion

Sentiment analysis concerns the study of opinions expressed in a text. Due to the huge amount of reviews, sentiment analysis plays a basic role to extract significant information and overall sentiment orientation of reviews. In this paper, we present a deep-learning-based method to classify a user's opinion expressed in reviews (called RNSA).To the best of our knowledge, a deep learning-based method in which a unified feature set which is representative of word embedding, sentiment knowledge, sentiment shifter rules, statistical and linguistic knowledge, has not been thoroughly studied for a sentiment analysis. The RNSA employs the Recurrent Neural Network (RNN) which is composed by Long Short-Term Memory (LSTM) to take advantage of sequential processing and overcome several flaws in traditional methods, where order and information about the word are vanished. Furthermore, it uses sentiment knowledge, sentiment shifter rules and multiple strategies to overcome the following drawbacks: words with similar semantic context but opposite sentiment polarity; contextual polarity; sentence types; word coverage limit of an individual lexicon; word sense variations. To verify the effectiveness of our work, we conduct sentence-level sentiment classification on large-scale review datasets. We obtained encouraging result. Experimental results show that (1) feature vectors in terms of (a) statistical, linguistic and sentiment knowledge, (b) sentiment shifter rules and (c) word-embedding can improve the classification accuracy of sentence-level sentiment analysis; (2) our method that learns from this unified feature set can obtain significant performance than one that learns from a feature subset; (3) our neural model yields superior performance improvements in comparison with other well-known approaches in the literature.     

A deep neural network model for coreference resolution in geological domain

Coreference resolution of geological entities is an important task in geological information mining. Although the existing generic coreference resolution models can handle geological texts, a dramatic decline in their performance can occur without sufficient domain knowledge. Due to the high diversity of geological terminology, coreference is intricately governed by the semantic and expressive structure of geological terms. In this paper, a framework CorefRoCNN based on RoBERTa and convolutional neural network (CNN) for end-to-end coreference resolution of geological entities is proposed. Firstly, the fine-tuned RoBERTa language model is used to transform words into dynamic vector representations with contextual semantic information. Second, a CNN-based multi-scale structure feature extraction module for geological terms is designed to capture the invariance of geological terms in length, internal structure, and distribution. Thirdly, we incorporate the structural feature and word embedding for further determinations of coreference relations. In addition, attention mechanisms are used to improve the ability of the model to capture valid information in geological texts with long sentence lengths. To validate the effectiveness of the model, we compared it with several state-of-the-art models on the constructed dataset. The results show that our model has the optimal performance with an average F1 value of 79.78%, which is a 1.22% improvement compared to the second-ranked method.     

Analyzing the discriminative attributes of products using text mining focused on cosmetic reviews

Consumers evaluate products through online reviews, in addition to sharing their product experiences. Online reviews affect product marketing, and companies use online reviews to investigate consumer attitudes and perceptions of their products. However, when analyzing a review, it is often the case that specific contexts are not taken into consideration and meaningful information is not obtained from the analysis results. This study suggests a methodology for analyzing reviews in the context of comparing two competing products. In addition, by analyzing the discriminative attributes of competing products, we were able to derive more specific information than an overall product analysis. Analyzing the discriminative attributes in the context of comparing competing products provides clarity on analyzing the strengths and weaknesses of competitive products and provides realistic information that can help the company's management activities. Considering this purpose, this study collected a review of the BB Cream product line in the cosmetics field. The analysis was sequentially carried out in three stages. First, we extracted words that represent discriminative attributes by analyzing the percentage difference of words. Second, different attribute words were classified according to the meaning used in the review by using latent semantic analysis. Finally, the polarity of discriminative attribute words was analyzed using Labeled-LDA. This analysis method can be used as a market research method as it can extract more information than a traditional survey or interview method, and can save cost and time through the automation of the program.     

A tale of two epidemics: Contextual Word2Vec for classifying twitter streams during outbreaks

Unstructured tweet feeds are becoming the source of real-time information for various events. However, extracting actionable information in real-time from this unstructured text data is a challenging task. Hence, researchers are employing word embedding approach to classify unstructured text data. We set our study in the contexts of the 2014 Ebola and 2016 Zika outbreaks and probed the accuracy of domain-specific word vectors for identifying crisis-related actionable tweets. Our findings suggest that relatively smaller domain-specific input corpora from the Twitter corpus are better in extracting meaningful semantic relationship than generic pre-trained Word2Vec (contrived from Google News) or GloVe (of Stanford NLP group). However, domain-specific quality tweet corpora during the early stages of outbreaks are normally scant, and identifying actionable tweets during early stages is crucial to stemming the proliferation of an outbreak. To overcome this challenge, we consider scholarly abstracts, related to Ebola and Zika virus, from PubMed and probe the efficiency of cross-domain resource utilization for word vector generation. Our findings demonstrate that the relevance of PubMed abstracts for the training purpose when Twitter data (as input corpus) would be scant during the early stages of the outbreak. Thus, this approach can be implemented to handle future outbreaks in real time. We also explore the accuracy of our word vectors for various model architectures and hyper-parameter settings. We observe that Skip-gram accuracies are better than CBOW, and higher dimensions yield better accuracy.     

Can we trace back hotel online reviews’ characteristics using gamification features?

Gamification is here to stay, and tourism and hospitality online review platforms are taking advantage of it to attract travelers and motivate them to contribute to their websites. Yet, literature in tourism is scarce in studying how effectively is users’ behavior changing through gamification features. This research aims at filling such gap through a data-driven approach based on a large volume of online reviews (a total of 67,685) collected from TripAdvisor between 2016 and 2017. Four artificial neural networks were trained to model title and review’s word length, and title and review’s sentiment score, using as input 12 gamification features used in TripAdvisor including points and badges. After validating the accuracy of the model for extracting knowledge, the data-based sensitivity analysis was applied to understand how each of the 12 features contributed to explaining review length and its sentiment score. Three badge features were considered the most relevant ones, including the total number of badges, the passport badges, and the explorer badges, providing evidence of a relation between gamification features and traveler’s behavior when writing reviews.     

Graph neural topic model with commonsense knowledge

Traditional topic models are based on the bag-of-words assumption, which states that the topic assignment of each word is independent of the others. However, this assumption ignores the relationship between words, which may hinder the quality of extracted topics. To address this issue, some recent works formulate documents as graphs based on word co-occurrence patterns. It assumes that if two words co-occur frequently, they should have the same topic. Nevertheless, it introduces noise edges into the model and thus hinders topic quality since two words co-occur frequently do not mean that they are on the same topic. In this paper, we use the commonsense relationship between words as a bridge to connect the words in each document. Compared to word co-occurrence, the commonsense relationship can explicitly imply the semantic relevance between words, which can be utilized to filter out noise edges. We use a relational graph neural network to capture the relation information in the graph. Moreover, manifold regularization is utilized to constrain the documents’ topic distributions. Experimental results on a public dataset show that our method is effective at extracting topics compared to baseline methods.     

Multilingual opinion mining on YouTube – A convolutional N-gram BiLSTM word embedding

Opinion mining in a multilingual and multi-domain environment as YouTube requires models to be robust across domains as well as languages, and not to rely on linguistic resources (e.g. syntactic parsers, POS-taggers, pre-defined dictionaries) which are not always available in many languages. In this work, we i) proposed a convolutional N-gram BiLSTM (CoNBiLSTM) word embedding which represents a word with semantic and contextual information in short and long distance periods; ii) applied CoNBiLSTM word embedding for predicting the type of a comment, its polarity sentiment (positive, neutral or negative) and whether the sentiment is directed toward the product or video; iii) evaluated the efficiency of our model on the SenTube dataset, which contains comments from two domains (i.e. automobile, tablet) and two languages (i.e. English, Italian). According to the experimental results, CoNBiLSTM generally outperforms the approach using SVM with shallow syntactic structures (STRUCT) – the current state-of-the-art sentiment analysis on the SenTube dataset. In addition, our model achieves more robustness across domains than the STRUCT (e.g. 7.47% of the difference in performance between the two domains for our model vs. 18.8% for the STRUCT)     

基于信号传递理论的在线评论有用性影响因素研究

[目的/意义]在线评论在消费者网络购物决策过程中解决信息不对称的作用日益显著,探索在线评论有用性影响因素对消费者和商家都具有重要意义。[方法/过程]以信号传递理论为框架,从与评论内容、评论者和反馈有关的信号构建在线评论有用性影响因素模型,同时考虑商品类型的调节作用,并分析了信号环境的影响。[结果/结论]通过亚马逊中国网站获取客观数据进行实证研究,发现负面评论、评论字数越多、评论含有图片、评论者对信息有披露、评论者排名越靠前、评论回应数量越多则评论有用性越高,商品类型在评论情感倾向、评论图片对评论有用性影响中起到了显著的调节作用,并且信号影响评论有用性受到信号环境的影响。     

Fine-grained image classification with factorized deep user click feature

The advantages of user click data greatly inspire its wide application in fine-grained image classification tasks. In previous click data based image classification approaches, each image is represented as a click frequency vector on a pre-defined query/word dictionary. However, this approach not only introduces high-dimensional issues, but also ignores the part of speech (POS) of a specific word as well as the word correlations. To address these issues, we devise the factorized deep click features to represent images. We first represent images as the factorized TF-IDF click feature vectors to discover word correlation, wherein several word dictionaries of different POS are constructed. Afterwards, we learn an end-to-end deep neural network on click feature tensors built on these factorized TF-IDF vectors. We evaluate our approach on the public Clickture-Dog dataset. It shows that: 1) the deep click feature learned on click tensor performs much better than traditional click frequency vectors; and 2) compared with many state-of-the-art textual representations, the proposed deep click feature is more discriminative and with higher classification accuracies.     

An analysis of cognitive change in online mental health communities: A textual data analysis based on post replies of support seekers

The replies of people seeking support in online mental health communities can be analyzed to discover if they feel better after receiving support; feeling better indicates a cognitive change. Most research uses key phrase matching and word frequency statistics to identify psychological cognitive change, methods that result in omissions and inaccuracy. This study constructs an intelligent method for identifying psychological cognitive change based on natural language processing technology. It incorporates information related to emotions that appears in reply text to help identify whether psychological cognitive change has occurred. The model first encodes the emotion information based on rule matching and manual annotation, then adds the encoded emotion lexicon and a cognitive change lexicon to a word2vec high-dimensional semantic word vector training, converts the annotated cognitive change recognition text into a vector matrix using the trained model, and train in the annotated text using TextCNN. To compare the results with those of the traditional methods (key phrase matching and sentiment word frequency statistics), this study uses a semi-automated approach to construct a lexicon of psychological cognitive change, as well as a keyword lexicon without cognitive change, based on word vectors and similarity. We compare the performance of the classifier before and after the fusion of the graphical emotion information, compare the LSTM and Transformer as baselines, and compare traditional word frequency statistics methods. The experimental results show that our proposed classification model performs better than the others; it achieves 84.38% precision, an 84.09% recall rate, and an 84.17% F1 value. Our work bears methodological implications for online mental health platforms.     

在线评论研究中的主题结构：社会网络分析的视角

探索在线评论相关领域中的研究主题以及它们之间的结构关系.从Web of Science核心数据库提取2009-2013年共113篇文献,通过共词分析确定了41个关键词,然后运用社会网络分析法识别了在线评论内容分析、在线评论深度挖掘、在线评论服务响应、在线评论行为研究、在线评论系统与社交媒体、在线评论与消费者决策、在线评论质量研究7个研究主题,最后提出一个新的研究框架为当前的研究提供参考.     

Unsupervised word sense disambiguation for Korean through the acyclic weighted digraph using corpus and dictionary

Word sense disambiguation (WSD) is meant to assign the most appropriate sense to a polysemous word according to its context. We present a method for automatic WSD using only two resources: a raw text corpus and a machine-readable dictionary (MRD). The system learns the similarity matrix between word pairs from the unlabeled corpus, and it uses the vector representations of sense definitions from MRD, which are derived based on the similarity matrix. In order to disambiguate all occurrences of polysemous words in a sentence, the system separately constructs the acyclic weighted digraph (AWD) for every occurrence of polysemous words in a sentence. The AWD is structured based on consideration of the senses of context words which occur with a target word in a sentence. After building the AWD per each polysemous word, we can search the optimal path of the AWD using the Viterbi algorithm. We assign the most appropriate sense to the target word in sentences with the sense on the optimal path in the AWD. By experiments, our system shows 76.4% accuracy for the semantically ambiguous Korean words.     

Semantic text classification: A survey of past and recent advances

Automatic text classification is the task of organizing documents into pre-determined classes, generally using machine learning algorithms. Generally speaking, it is one of the most important methods to organize and make use of the gigantic amounts of information that exist in unstructured textual format. Text classification is a widely studied research area of language processing and text mining. In traditional text classification, a document is represented as a bag of words where the words in other words terms are cut from their finer context i.e. their location in a sentence or in a document. Only the broader context of document is used with some type of term frequency information in the vector space. Consequently, semantics of words that can be inferred from the finer context of its location in a sentence and its relations with neighboring words are usually ignored. However, meaning of words, semantic connections between words, documents and even classes are obviously important since methods that capture semantics generally reach better classification performances. Several surveys have been published to analyze diverse approaches for the traditional text classification methods. Most of these surveys cover application of different semantic term relatedness methods in text classification up to a certain degree. However, they do not specifically target semantic text classification algorithms and their advantages over the traditional text classification. In order to fill this gap, we undertake a comprehensive discussion of semantic text classification vs. traditional text classification. This survey explores the past and recent advancements in semantic text classification and attempts to organize existing approaches under five fundamental categories; domain knowledge-based approaches, corpus-based approaches, deep learning based approaches, word/character sequence enhanced approaches and linguistic enriched approaches. Furthermore, this survey highlights the advantages of semantic text classification algorithms over the traditional text classification algorithms.     

A benchmark for evaluating Arabic contextualized word embedding models

Word embeddings, which represent words as numerical vectors in a high-dimensional space, are contextualized by generating a unique vector representation for each sense of a word based on the surrounding words and sentence structure. They are typically generated using such deep learning models as BERT and trained on large amounts of text data and using self-supervised learning techniques. Resulting embeddings are highly effective at capturing the nuances of language, and have been shown to significantly improve the performance of numerous NLP tasks. Word embeddings represent textual records of human thinking, with all the mental relations that we utilize to produce the succession of sentences that make up texts and discourses. Consequently, the distributed representation of words within embeddings ought to capture the reasoning relations that hold texts together. This paper makes its contribution to the field by proposing a benchmark for the assessment of contextualized word embeddings that probes into their capability for true contextualization by inspecting how well they capture resemblance, contrariety, comparability, identity, relations in time and space, causation, analogy, and sense disambiguation. The proposed metrics adopt a triangulation approach, so they use (1) Hume’s reasoning relations, (2) standard analogy, and (3) sense disambiguation. The benchmark has been evaluated against 22 Arabic contextualized embeddings and has proven to be capable of quantifying their differential performance in terms of these reasoning relations. Results of evaluation of the target embeddings revealed that they do take context into account and that they do reasonably well in sense disambiguation but have weakness in their identification of converseness, synonymy, complementarity, and analogy. Results also show that size of an embedding has diminishing returns because the highly frequent language patterns swamp low frequency patterns. Furthermore, the suggest that future research endeavors should not be concerned with the quantity of data as much as its quality, and that it should focus more on the representativeness of data, and on model architecture, design, and training.     

QMOS: Query-based multi-documents opinion-oriented summarization

Sentiment analysis concerns the study of opinions expressed in a text. This paper presents the QMOS method, which employs a combination of sentiment analysis and summarization approaches. It is a lexicon-based method to query-based multi-documents summarization of opinion expressed in reviews.QMOS combines multiple sentiment dictionaries to improve word coverage limit of the individual lexicon. A major problem for a dictionary-based approach is the semantic gap between the prior polarity of a word presented by a lexicon and the word polarity in a specific context. This is due to the fact that, the polarity of a word depends on the context in which it is being used. Furthermore, the type of a sentence can also affect the performance of a sentiment analysis approach. Therefore, to tackle the aforementioned challenges, QMOS integrates multiple strategies to adjust word prior sentiment orientation while also considers the type of sentence. QMOS also employs the Semantic Sentiment Approach to determine the sentiment score of a word if it is not included in a sentiment lexicon.On the other hand, the most of the existing methods fail to distinguish the meaning of a review sentence and user's query when both of them share the similar bag-of-words; hence there is often a conflict between the extracted opinionated sentences and users’ needs. However, the summarization phase of QMOS is able to avoid extracting a review sentence whose similarity with the user's query is high but whose meaning is different. The method also employs the greedy algorithm and query expansion approach to reduce redundancy and bridge the lexical gaps for similar contexts that are expressed using different wording, respectively. Our experiment shows that the QMOS method can significantly improve the performance and make QMOS comparable to other existing methods.     

自动分词中智能词典的研究

现阶段,绝大多数自动分词系统都是基于词典的方法,词典的完备性是决定分词系统性能的基础和关键,但词典的完备性一直都是很难完善的。本文介绍了机械分词法与无词典分词法,并利用两种分词法各自的优点将其整合,提出了具有自学习功能的智能词典这个概念,以弥补分词词典无法完备的缺陷。