Integrated microblog sentiment analysis from users’ social interaction patterns and textual opinions

Traditional post-level opinion classification methods usually fail to capture a person’s overall sentiment orientation toward a topic from his/her microblog posts published for a variety of themes related to that topic. One reason for this is that the sentiments connoted in the textual expressions of microblog posts are often obscure. Moreover, a person’s opinions are often influenced by his/her social network. This study therefore proposes a new method based on integrated information of microblog users’ social interactions and textual opinions to infer the sentiment orientation of a user or the whole group regarding a hot topic. A Social Opinion Graph (SOG) is first constructed as the data model for sentiment analysis of a group of microblog users who share opinions on a topic. This represents their social interactions and opinions. The training phase then uses the SOGs of training sets to construct Sentiment Guiding Matrix (SGM), representing the knowledge about the correlation between users’ sentiments, Textual Sentiment Classifier (TSC), and emotion homophily coefficients of the influence of various types of social interaction on users’ mutual sentiments. All of these support a high-performance social sentiment analysis procedure based on the relaxation labeling scheme. The experimental results show that the proposed method has better sentiment classification accuracy than the textual classification and other integrated classification methods. In addition, IMSA can reduce pre-annotation overheads and the influence from sampling deviation.     

Combining global, regional and contextual features for automatic image annotation

This paper presents a novel approach to automatic image annotation which combines global, regional, and contextual features by an extended cross-media relevance model. Unlike typical image annotation methods which use either global or regional features exclusively, as well as neglect the textual context information among the annotated words, the proposed approach incorporates the three kinds of information which are helpful to describe image semantics to annotate images by estimating their joint probability. Specifically, we describe the global features as a distribution vector of visual topics and model the textual context as a multinomial distribution. The global features provide the global distribution of visual topics over an image, while the textual context relaxes the assumption of mutual independence among annotated words which is commonly adopted in most existing methods. Both the global features and textual context are learned by a probability latent semantic analysis approach from the training data. The experiments over 5k Corel images have shown that combining these three kinds of information is beneficial in image annotation.     

A multidimensional approach for detecting irony in Twitter

Irony is a pervasive aspect of many online texts, one made all the more difficult by the absence of face-to-face contact and vocal intonation. As our media increasingly become more social, the problem of irony detection will become even more pressing. We describe here a set of textual features for recognizing irony at a linguistic level, especially in short texts created via social media such as Twitter postings or “tweets”. Our experiments concern four freely available data sets that were retrieved from Twitter using content words (e.g. “Toyota”) and user-generated tags (e.g. “#irony”). We construct a new model of irony detection that is assessed along two dimensions: representativeness and relevance. Initial results are largely positive, and provide valuable insights into the figurative issues facing tasks such as sentiment analysis, assessment of online reputations, or decision making.     

面向评论信息的跨领域词汇情感倾向判别方法

词汇的情感倾向判别对文本情感分类具有重要意义。已有方法多假设存在基准词,根据目标词与基准词的关联度来判别目标词的情感倾向。实际应用中,尤其是评论语料库中基准词往往存在情感歧义问题,从而影响判别结果的准确性。基于上述分析,面向给定语料库,提出一种基准词的提取和消歧方法,并在此基础上实现跨领域的词汇情感倾向判别。首先在任一标记语料库中自动提取候选基准词;然后基于共现矩阵评估并过滤部分具有情感歧义的基准词;最后通过计算基准词与目标词的相似性,实现目标词的情感倾向判别。实验结果表明了方法的有效性和可行性。     

Multimodal Retrieval using Mutual Information based Textual Query Reformulation

Multimodal Retrieval is a well-established approach for image retrieval. Usually, images are accompanied by text caption along with associated documents describing the image. Textual query expansion as a form of enhancing image retrieval is a relatively less explored area. In this paper, we first study the effect of expanding textual query on both image and its associated text retrieval. Our study reveals that judicious expansion of textual query through keyphrase extraction can lead to better results, either in terms of text-retrieval or both image and text-retrieval. To establish this, we use two well-known keyphrase extraction techniques based on tf-idf and KEA. While query expansion results in increased retrieval efficiency, it is imperative that the expansion be semantically justified. So, we propose a graph-based keyphrase extraction model that captures the relatedness between words in terms of both mutual information and relevance feedback. Most of the existing works have stressed on bridging the semantic gap by using textual and visual features, either in combination or individually. The way these text and image features are combined determines the efficacy of any retrieval. For this purpose, we adopt Fisher-LDA to adjudge the appropriate weights for each modality. This provides us with an intelligent decision-making process favoring the feature set to be infused into the final query. Our proposed algorithm is shown to supersede the previously mentioned keyphrase extraction algorithms for query expansion significantly. A rigorous set of experiments performed on ImageCLEF-2011 Wikipedia Retrieval task dataset validates our claim that capturing the semantic relation between words through Mutual Information followed by expansion of a textual query using relevance feedback can simultaneously enhance both text and image retrieval.     

ACNN-TL: attention-based convolutional neural network coupling with transfer learning and contextualized word representation for enhancing the performance of sentiment classification

Due to the rapid growth of textual information on the web, analyzing users' opinions about particular products, events or services is now considered a crucial and challenging task that has changed sentiment analysis from an academic endeavor to an essential analytic tool in cognitive science and natural language understanding. Despite the remarkable success of deep learning models for textual sentiment classification, they are still confronted with some limitations. Convolutional neural network is one of the deep learning models that has been excelled at sentiment classification but tends to need a large amount of training data while it considers that all words in a sentence have equal contribution in the polarity of a sentence and its performance is highly dependent on its accompanying hyper-parameters. To overcome these issues, an Attention-Based Convolutional Neural Network with Transfer Learning (ACNN-TL) is proposed in this paper that not only tries to take advantage of both attention mechanism and transfer learning to boost the performance of sentiment classification but also language models, namely Word2Vec and BERT, are used as its the backbone to better express sentence semantics as word vector. We conducted our experiment on widely-studied sentiment classification datasets and according to the empirical results, not only the proposed ACNN-TL achieved comparable or even better classification results but also employing contextual representation and transfer learning yielded remarkable improvement in the classification accuracy.

     

Continuous monitoring of range spatial keyword query over moving objects

In this paper, we propose an efficient solution for processing continuous range spatial keyword queries over moving spatio-textual objects (namely, CRSK-mo queries). Major challenges in efficient processing of CRSK-mo queries are as follows: (i) the query range is determined based on both spatial proximity and textual similarity; thus a straightforward spatial proximity based pruning of the search space is not applicable as any object far from a query location with a high textual similarity score can still be the answer (and vice versa), (ii) frequent location updates may invalidate a query result, and thus require frequent re-computing of the result set for any object updates. To address these challenges, the key idea of our approach is to exploit the spatial and textual upper bounds between queries and objects to form safe zones (at the client-side) and buffer regions (at the server-side), and then use these bounds to quickly prune objects and queries through smart in-memory data structures. We conduct extensive experiments with a synthetic dataset that verify the effectiveness and efficiency of our proposed algorithm.     

The Method for Extracting New Login Sentiment Words from Chinese Micro-Blog Basedf on Improved Mutual Information

The current method of extracting new login sentiment words not only ignores the diversity of patterns constituted by new multi-character words (the number of words is greater than two), but also disregards the influence of other new words co-occurring with a new word connoting sentiment. To solve this problem, this paper proposes a method for extracting new login sentiment words from Chinese micro-blog based on improved mutual information. First, micro-blog data are preprocessed, taking into consideration some nonsense signals such as web links and punctuation. Based on preprocessed data, the candidate strings are obtained by applying the N-gram segmentation method. Then, the extraction algorithm for new login words is proposed, which combines multi-character mutual information (MMI) and left and right adjacent entropy. In this algorithm, the MMI describes the internal cohesion of the candidate string of multiple words in a variety of constituted patterns. Then, the candidate strings are extended and filtered according to frequency, MMI, and right and left adjacency entropy, to extract new login words. Finally, the algorithm for the extraction of new login sentiment words is proposed. In this algorithm, the Sentiment Similarity between words (SW) is determined in order to measure the sentiment similarity of a new login word to other sentiment words and other new login sentiment words. Then, the sentiment tendency values of new login words are obtained by calculating the SW to extract new login sentiment words. Experimental results show that this method is very effective for the extraction of new login sentiment words.     

Overlapping correlation clustering

We introduce a new approach for finding overlapping clusters given pairwise similarities of objects. In particular, we relax the problem of correlation clustering by allowing an object to be assigned to more than one cluster. At the core of our approach is an optimization problem in which each data point is mapped to a small set of labels, representing membership in different clusters. The objective is to find a mapping so that the given similarities between objects agree as much as possible with similarities taken over their label sets. The number of labels can vary across objects. To define a similarity between label sets, we consider two measures: (i) a 0–1 function indicating whether the two label sets have non-zero intersection and (ii) the Jaccard coefficient between the two label sets. The algorithm we propose is an iterative local-search method. The definitions of label set similarity give rise to two non-trivial optimization problems, which, for the measures of set-intersection and Jaccard, we solve using a greedy strategy and non-negative least squares, respectively. We also develop a distributed version of our algorithm based on the BSP model and implement it using a Pregel framework. Our algorithm uses as input pairwise similarities of objects and can thus be applied when clustering structured objects for which feature vectors are not available. As a proof of concept, we apply our algorithms on three different and complex application domains: trajectories, amino-acid sequences, and textual documents.     

Detecting,classifying, and tracing non-functional software requirements

In this paper, we describe a novel unsupervised approach for detecting, classifying, and tracing non-functional software requirements (NFRs). The proposed approach exploits the textual semantics of software functional requirements (FRs) to infer potential quality constraints enforced in the system. In particular, we conduct a systematic analysis of a series of word similarity methods and clustering techniques to generate semantically cohesive clusters of FR words. These clusters are classified into various categories of NFRs based on their semantic similarity to basic NFR labels. Discovered NFRs are then traced to their implementation in the solution space based on their textual semantic similarity to source code artifacts. Three software systems are used to conduct the experimental analysis in this paper. The results show that methods that exploit massive sources of textual human knowledge are more accurate in capturing and modeling the notion of similarity between FR words in a software system. Results also show that hierarchical clustering algorithms are more capable of generating thematic word clusters than partitioning clustering techniques. In terms of performance, our analysis indicates that the proposed approach can discover, classify, and trace NFRs with accuracy levels that can be adequate for practical applications.     

Exploiting semantic relationships for unsupervised expansion of sentiment lexicons

The literature in sentiment analysis has widely assumed that semantic relationships between words cannot be effectively exploited to produce satisfactory sentiment lexicon expansions. This assumption stems from the fact that words considered to be “close” in a semantic space (e.g., word embeddings) may present completely opposite polarities, which might suggest that sentiment information in such spaces is either too faint, or at least not readily exploitable. Our main contribution in this paper is a rigorous and robust challenge to this assumption: by proposing a set of theoretical hypotheses and corroborating them with strong experimental evidence, we demonstrate that semantic relationships can be effectively used for good lexicon expansion. Based on these results, our second contribution is a novel, simple, and yet effective lexicon-expansion strategy based on semantic relationships extracted from word embeddings. This strategy is able to substantially enhance the lexicons, whilst overcoming the major problem of lexicon coverage. We present an extensive experimental evaluation of sentence-level sentiment analysis, comparing our approach to sixteen state-of-the-art (SOTA) lexicon-based and five lexicon expansion methods, over twenty datasets. Results show that in the vast majority of cases our approach outperforms the alternatives, achieving coverage of almost 100% and gains of about 26% against the best baselines. Moreover, our unsupervised approach performed competitively against SOTA supervised sentiment analysis methods, mainly in scenarios with scarce information. Finally, in a cross-dataset comparison, our approach turned out to be as competitive as (i.e., statistically tie with) state-of-the-art supervised solutions such as pre-trained transformers (BERT), even without relying on any training (labeled) data. Indeed in small datasets or in datasets with scarce information (short messages), our solution outperformed the supervised ones by large margins.     

Ontology-based semantic similarity: A new feature-based approach

Estimation of the semantic likeness between words is of great importance in many applications dealing with textual data such as natural language processing, knowledge acquisition and information retrieval. Semantic similarity measures exploit knowledge sources as the base to perform the estimations. In recent years, ontologies have grown in interest thanks to global initiatives such as the Semantic Web, offering an structured knowledge representation. Thanks to the possibilities that ontologies enable regarding semantic interpretation of terms many ontology-based similarity measures have been developed. According to the principle in which those measures base the similarity assessment and the way in which ontologies are exploited or complemented with other sources several families of measures can be identified. In this paper, we survey and classify most of the ontology-based approaches developed in order to evaluate their advantages and limitations and compare their expected performance both from theoretical and practical points of view. We also present a new ontology-based measure relying on the exploitation of taxonomical features. The evaluation and comparison of our approach’s results against those reported by related works under a common framework suggest that our measure provides a high accuracy without some of the limitations observed in other works.     

TF–DF indexing for mocap data segments in measuring relevance based on textual search queries

Many techniques have been proposed to address the problem of mocap data retrieval by using a short motion as input, and they are commonly categorized as content-based retrieval. However, it is difficult for users who do not have equipments to create mocap data samples to take advantage of them. On the contrary, simple retrieval methods which only require text as input can be used by everyone. Nevertheless, not only that it is not clear how to measure mocap data relevance in regard to textual search queries, but the search results will also be limited to the mocap data samples, the annotations of which contain the words in the search query. In this paper, the authors propose a novel method that builds on the TF (term frequency) and IDF (inverse document frequency) weights, commonly used in text document retrieval, to measure mocap data relevance in regard to textual search queries. We extract segments from mocap data samples and regard these segments as words in text documents. However, instead of using IDF which prioritizes infrequent segments, we opt to use DF (document frequency) to prioritize frequent segments. Since motions are not required as input, everybody will be able to take advantage of our approach, and we believe that our work also opens up possibilities for applying developed text retrieval methods in mocap data retrieval.     

Sentimental causal rule discovery from Twitter

Social media, especially Twitter is now one of the most popular platforms where people can freely express their opinion. However, it is difficult to extract important summary information from many millions of tweets sent every hour. In this work we propose a new concept, sentimental causal rules, and techniques for extracting sentimental causal rules from textual data sources such as Twitter which combine sentiment analysis and causal rule discovery. Sentiment analysis refers to the task of extracting public sentiment from textual data. The value in sentiment analysis lies in its ability to reflect popularly voiced perceptions that are stated in natural language. Causal rules on the other hand indicate associations between different concepts in a context where one (or several concepts) cause(s) the other(s). We believe that sentimental causal rules are an effective summarization mechanism that combine causal relations among different aspects extracted from textual data as well as the sentiment embedded in these causal relationships. In order to show the effectiveness of sentimental causal rules, we have conducted experiments on Twitter data collected on the Kurdish political issue in Turkey which has been an ongoing heated public debate for many years. Our experiments on Twitter data show that sentimental causal rule discovery is an effective method to summarize information about important aspects of an issue in Twitter which may further be used by politicians for better policy making.     

A collaborative user-centered framework for recommending items in Online Social Networks

Recommender Systems are more and more playing an important role in our life, representing useful tools helping users to find “what they need” from a very large number of candidates and supporting people in making decisions in various contexts: what items to buy, which movie to watch, or even who they can invite to their social network, etc. In this paper, we propose a novel collaborative user-centered recommendation approach in which several aspects related to users and available in Online Social Networks – i.e. preferences (usually in the shape of items’ metadata), opinions (textual comments to which it is possible to associate a sentiment), behavior (in the majority of cases logs of past items’ observations made by users), feedbacks (usually expressed in the form of ratings) – are considered and integrated together with items’ features and context information within a general framework that can support different applications using proper customizations (e.g., recommendation of news, photos, movies, travels, etc.). Experiments on system accuracy and user satisfaction in several domains shows how our approach provides very promising and interesting results.     

A case study of Spanish text transformations for twitter sentiment analysis

Sentiment analysis is a text mining task that determines the polarity of a given text, i.e., its positiveness or negativeness. Recently, it has received a lot of attention given the interest in opinion mining in micro-blogging platforms. These new forms of textual expressions present new challenges to analyze text because of the use of slang, orthographic and grammatical errors, among others. Along with these challenges, a practical sentiment classifier should be able to handle efficiently large workloads.The aim of this research is to identify in a large set of combinations which text transformations (lemmatization, stemming, entity removal, among others), tokenizers (e.g., word n-grams), and token-weighting schemes make the most impact on the accuracy of a classifier (Support Vector Machine) trained on two Spanish datasets. The methodology used is to exhaustively analyze all combinations of text transformations and their respective parameters to find out what common characteristics the best performing classifiers have. Furthermore, we introduce a novel approach based on the combination of word-based n-grams and character-based q-grams. The results show that this novel combination of words and characters produces a classifier that outperforms the traditional word-based combination by 11.17% and 5.62% on the INEGI and TASS’15 dataset, respectively.     

结合卷积神经网络和词语情感序列特征的中文情感分析

目前基于词嵌入的卷积神经网络文本分类方法已经在情感分析研究中取得了很好的效果。此类方法主要使用基于上下文的词嵌入特征,但在词嵌入过程中通常并未考虑词语本身的情感极性,同时此类方法往往缺乏对大量人工构建情感词典等资源的有效利用。针对这些问题,该文提出了一种结合情感词典和卷积神经网络的情感分类方法,利用情感词典中的词条对文本中的词语进行抽象表示,在此基础上利用卷积神经网络提取抽象词语的序列特征,并用于情感极性分类。该文提出的相关方法在中文倾向性分析评测COAE2014数据集上取得了比目前主流的卷积神经网络以及朴素贝叶斯支持向量机更好的性能。     

A valences-totaling model for English sentiment classification

Sentiment classification plays an important role in everyday life, in political activities, activities of commodity production and commercial activities. Finding a time-effective and highly accurate solution to the classification of emotions is challenging. Today, there are many models (or methods) to classify the sentiment of documents. Sentiment classification has been studied for many years and is used widely in many different fields. We propose a new model, which is called the valences-totaling model (VTM), by using cosine measure (CM) to classify the sentiment of English documents. VTM is a new model for English sentiment classification. In this study, CM is a measure of similarity between two words and is used to calculate the valence (and polarity) of English semantic lexicons. We prove that CM is able to identify the sentiment valence and the sentiment polarity of the English sentiment lexicons online in combination with the Google search engine with AND operator and OR operator. VTM uses many English semantic lexicons. These English sentiment lexicons are calculated online and are based on the Internet. We present a full range of English sentences; thus, the emotion expressed in the English text is classified with more precision. Our new model is not dependent on a special domain and training data set—it is a domain-independent classifier. We test our new model on the Internet data in English. The calculated valence (and polarity) of English semantic words in this model is based on many documents on millions of English Web sites and English social networks.     

A novel deterministic approach for aspect-based opinion mining in tourism products reviews

This work proposes an extension of Bing Liu’s aspect-based opinion mining approach in order to apply it to the tourism domain. The extension concerns with the fact that users refer differently to different kinds of products when writing reviews on the Web. Since Liu’s approach is focused on physical product reviews, it could not be directly applied to the tourism domain, which presents features that are not considered by the model. Through a detailed study of on-line tourism product reviews, we found these features and then model them in our extension, proposing the use of new and more complex NLP-based rules for the tasks of subjective and sentiment classification at the aspect-level. We also entail the task of opinion visualization and summarization and propose new methods to help users digest the vast availability of opinions in an easy manner. Our work also included the development of a generic architecture for an aspect-based opinion mining tool, which we then used to create a prototype and analyze opinions from TripAdvisor in the context of the tourism industry in Los Lagos, a Chilean administrative region also known as the Lake District. Results prove that our extension is able to perform better than Liu’s model in the tourism domain, improving both Accuracy and Recall for the tasks of subjective and sentiment classification. Particularly, the approach is very effective in determining the sentiment orientation of opinions, achieving an F-measure of 92% for the task. However, on average, the algorithms were only capable of extracting 35% of the explicit aspect expressions, using a non-extended approach for this task. Finally, results also showed the effectiveness of our design when applied to solving the industry’s specific issues in the Lake District, since almost 80% of the users that used our tool considered that our tool adds valuable information to their business.