In this paper, we introduce a new framework called the sentiment-aspect attribution module (SAAM). SAAM works on top of traditional neural networks and is designed to address the problem of multi-aspect sentiment classification and sentiment regression. The framework works by exploiting the correlations between sentence-level embedding features and variations of document-level aspect rating scores. We demonstrate several variations of our framework on top of CNN and RNN based models. Experiments on a hotel review dataset and a beer review dataset have shown SAAM can improve sentiment analysis performance over corresponding base models. Moreover, because of the way our framework intuitively combines sentence-level scores into document-level scores, it is able to provide a deeper insight into data (e.g., semi-supervised sentence aspect labeling). Hence, we end the paper with a detailed analysis that shows the potential of our models for other applications such as sentiment snippet extraction.
Interpreting Sentiment Composition with Latent Semantic Tree
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Meituan（美团）
When a model attribution technique highlights a particular part of the input, a user might understand this highlight as making a statement about counterfactuals (Miller, 2019): if that part of the input were to change, the model's prediction might change as well. This paper investigates how well different attribution techniques align with this assumption on realistic counterfactuals in the case of reading comprehension (RC). RC is a particularly challenging test case, as token-level attributions that have been extensively studied in other NLP tasks such as sentiment analysis are less suitable …
Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agents
University of Manchester（曼彻斯特大学）；University of Sheffield（谢菲尔德大学）；Idiap Research Institute（Idiap研究 institute）；National Biomarker Centre, CRUK-MI, University of Manchester（国家生物标志物中心，CRUK-MI，曼彻斯特大学）
Generative Sentiment Analysis via Latent Category Distribution and Constrained Decoding
School of Cyber Science and Engineering, Wuhan University（武汉大学网络科学与工程学院）；Beijing Rigour Technology Co., Ltd.（北京睿格科技有限公司）；School of Cyberspace, Hangzhou Dianzi University（杭州电子科技大学网络空间学院）；North China Power Engineering Co., Ltd. of China Power Engineering Consulting Group（中国电力工程顾问集团华北电力工程有限公司）
University College London（伦敦大学学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Microsoft Research（微软研究院）；University of Cambridge（剑桥大学）；University of Copenhagen（哥本哈根大学）
When assigning quantitative labels to a dataset, different methodologies may rely on different scales. In particular, when assigning polarities to words in a sentiment lexicon, annotators may use binary, categorical, or continuous labels. Naturally, it is of interest to unify these labels from disparate scales to both achieve maximal coverage over words and to create a single, more robust sentiment lexicon while retaining scale coherence. We introduce a generative model of sentiment lexica to combine disparate scales into a common latent representation. We realize this model with a novel multi…
Stanford University（斯坦福大学）；National University of Singapore（新加坡国立大学）
BERT, as one of the pretrianed language models, attracts the most attention in recent years for creating new benchmarks across GLUE tasks via fine-tuning. One pressing issue is to open up the blackbox and explain the decision makings of BERT. A number of attribution techniques have been proposed to explain BERT models, but are often limited to sequence to sequence tasks. In this paper, we adapt existing attribution methods on explaining decision makings of BERT in sequence classification tasks. We conduct extensive analyses of four existing attribution methods by applying them to four differen…
University of Toronto（多伦多大学）；University of Pittsburgh（匹兹堡大学）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）
The study aims to understand Twitter users' discourse and psychological reactions to COVID-19. We use machine learning techniques to analyze about 1.9 million Tweets (written in English) related to coronavirus collected from January 23 to March 7, 2020. A total of salient 11 topics are identified and then categorized into ten themes, including "updates about confirmed cases," "COVID-19 related death," "cases outside China (worldwide)," "COVID-19 outbreak in South Korea," "early signs of the outbreak in New York," "Diamond Princess cruise," "economic impact," "Preventive measures," "authorities…
Aspect-term sentiment analysis (ATSA) is a longstanding challenge in natural language understanding. It requires fine-grained semantical reasoning about a target entity appeared in the text. As manual annotation over the aspects is laborious and time-consuming, the amount of labeled data is limited for supervised learning. This paper proposes a semi-supervised method for the ATSA problem by using the Variational Autoencoder based on Transformer (VAET), which models the latent distribution via variational inference. By disentangling the latent representation into the aspect-specific sentiment a…
AWS AI Labs（AWS人工智能实验室）；Amazon Core AI（亚马逊核心人工智能部）；North Carolina State University（北卡罗来纳州立大学）
With the growing popularity of deep-learning models, model understanding becomes more important. Much effort has been devoted to demystify deep neural networks for better interpretability. Some feature attribution methods have shown promising results in computer vision, especially the gradient-based methods where effectively smoothing the gradients with reference data is key to a robust and faithful result. However, direct application of these gradient-based methods to NLP tasks is not trivial due to the fact that the input consists of discrete tokens and the "reference" tokens are not explici…
Stanford University（斯坦福大学）；Institute of High Performance Computing, Agency for Science, Technology and Research（科学技术研究局高性能计算研究所）；National University of Singapore（新加坡国立大学）
Neural attention, especially the self-attention made popular by the Transformer, has become the workhorse of state-of-the-art natural language processing (NLP) models. Very recent work suggests that the self-attention in the Transformer encodes syntactic information; Here, we show that self-attention scores encode semantics by considering sentiment analysis tasks. In contrast to gradient-based feature attribution methods, we propose a simple and effective Layer-wise Attention Tracing (LAT) method to analyze structured attention weights. We apply our method to Transformer models trained on two …
University of Edinburgh（爱丁堡大学）；University of Amsterdam（阿姆斯特丹大学）
We treat projective dependency trees as latent variables in our probabilistic model and induce them in such a way as to be beneficial for a downstream task, without relying on any direct tree supervision. Our approach relies on Gumbel perturbations and differentiable dynamic programming. Unlike previous approaches to latent tree learning, we stochastically sample global structures and our parser is fully differentiable. We illustrate its effectiveness on sentiment analysis and natural language inference tasks. We also study its properties on a synthetic structure induction task. Ablation studi…
An increasing number of people are using online social networking services (SNSs), and a significant amount of information related to experiences in consumption is shared in this new media form. Text mining is an emerging technique for mining useful information from the web. We aim at discovering in particular tweets semantic patterns in consumers' discussions on social media. Specifically, the purposes of this study are twofold: 1) finding similarity and dissimilarity between two sets of textual documents that include consumers' sentiment polarities, two forms of positive vs. negative opinion…
Divide and Conquer: Mixture-of-Bottleneck Experts in Informative Ordinal Space for Video-based Multimodal Sentiment Analysis
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；School of Electronics and Information Technology, Sun Yat-sen University（中山大学电子信息工程学院）；School of Cyberspace Security, Guangzhou University（广州大学网络空间安全学院）；School of Computer Science, South China Normal University（华南师范大学计算机学院）；VinUniversity（越南河内VinUniversity）；Nanyang Technological University（南洋理工大学）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Desay SV Automotive Co., Ltd（德赛西威汽车电子股份有限公司）
In recent times, word embeddings are taking a significant role in sentiment analysis. As the generation of word embeddings needs huge corpora, many applications use pretrained embeddings. In spite of the success, word embeddings suffers from certain drawbacks such as it does not capture sentiment information of a word, contextual information in terms of parts of speech tags and domain-specific information. In this work we propose HIDE a Hybrid Improved Document level Embedding which incorporates domain information, parts of speech information and sentiment information into existing word embedd…
National University of Singapore（新加坡国立大学）；SAP Innovation Center Singapore（SAP新加坡创新中心）
Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence. This task is usually done in a pipeline manner, with aspect term extraction performed first, followed by sentiment predictions toward the extracted aspect terms. While easier to develop, such an approach does not fully exploit joint information from the two subtasks and does not use all available sources of training information that might be helpful, such as document-level labeled sentiment corpus. In this paper, we propose an interactive multi-task learning netwo…
When people buy products online, they primarily base their decisions on the recommendations of others given in online reviews. The current work analyzed these online reviews by sentiment analysis and used the extracted sentiments as features to predict the product ratings by several machine learning algorithms. These predictions were disentangled by various meth-ods of explainable AI (XAI) to understand whether the model showed any bias during prediction. Study 1 benchmarked these algorithms (knn, support vector machines, random forests, gradient boosting machines, XGBoost) and identified rand…
Zhejiang University（浙江大学）；Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entropy-based methods for the task, which suffer from instability and poor generalization. In this paper, we explore contrastive learning on the cross-domain sentiment analysis task. We propose a modified contrastive objective with in-batch negative samples so that the sentence representations from the same class will be pushed close while those from the different classes become furt…
Hong Kong University of Science and Technology（香港科技大学）；University of Southern California（南加州大学）；University of Hong Kong（香港大学）
In this paper, we propose a variational approach to unsupervised sentiment analysis. Instead of using ground truth provided by domain experts, we use target-opinion word pairs as a supervision signal. For example, in a document snippet "the room is big," (room, big) is a target-opinion word pair. These word pairs can be extracted by using dependency parsers and simple rules. Our objective function is to predict an opinion word given a target word while our ultimate goal is to learn a sentiment classifier. By introducing a latent variable, i.e., the sentiment polarity, to the objective function…
ANU & NICTA（澳大利亚国立大学与NICTA）；Monash University（莫纳什大学）
Aspect-based opinion mining is widely applied to review data to aggregate or summarize opinions of a product, and the current state-of-the-art is achieved with Latent Dirichlet Allocation (LDA)-based model. Although social media data like tweets are laden with opinions, their "dirty" nature (as natural language) has discouraged researchers from applying LDA-based opinion model for product review mining. Tweets are often informal, unstructured and lacking labeled data such as categories and ratings, making it challenging for product opinion mining. In this paper, we propose an LDA-based opinion…
Over the last few years, machine learning over graph structures has manifested a significant enhancement in text mining applications such as event detection, opinion mining, and news recommendation. One of the primary challenges in this regard is structuring a graph that encodes and encompasses the features of textual data for the effective machine learning algorithm. Besides, exploration and exploiting of semantic relations is regarded as a principal step in text mining applications. However, most of the traditional text mining methods perform somewhat poor in terms of employing such relation…
The growing popularity of social media (e.g, Twitter) allows users to easily share information with each other and influence others by expressing their own sentiments on various subjects. In this work, we propose an unsupervised \emph{tri-clustering} framework, which analyzes both user-level and tweet-level sentiments through co-clustering of a tripartite graph. A compelling feature of the proposed framework is that the quality of sentiment clustering of tweets, users, and features can be mutually improved by joint clustering. We further investigate the evolution of user-level sentiments and l…
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；Tencent AI Lab（腾讯人工智能实验室）；Alibaba DAMO Academy（阿里巴巴达摩院）；Southern University of Science and Technology（南方科技大学）
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferr…
This thesis explores the ways by how people express their opinions on German Twitter, examines current approaches to automatic mining of these feelings, and proposes novel methods, which outperform state-of-the-art techniques. For this purpose, I introduce a new corpus of German tweets that have been manually annotated with sentiments, their targets and holders, as well as polar terms and their contextual modifiers. Using these data, I explore four major areas of sentiment research: (i) generation of sentiment lexicons, (ii) fine-grained opinion mining, (iii) message-level polarity classificat…
FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis
School of Artificial Intelligence, Beihang University, China（北京航空航天大学人工智能学院）；School of Computer Science and Engineering, Beihang University, China（北京航空航天大学计算机科学与工程学院）；Xidian University, China（西安电子科技大学）；Zhongguancun Laboratory, China（中关村实验室）
University of Galway（戈尔韦大学）；Technological University Dublin（都柏林理工大学）
Internet memes are characterised by the interspersing of text amongst visual elements. State-of-the-art multimodal meme classifiers do not account for the relative positions of these elements across the two modalities, despite the latent meaning associated with where text and visual elements are placed. Against two meme sentiment classification datasets, we systematically show performance gains from incorporating the spatial position of visual objects, faces, and text clusters extracted from memes. In addition, we also present facial embedding as an impactful enhancement to image representatio…
Prediction and quantification of future volatility and returns play an important role in financial modelling, both in portfolio optimization and risk management. Natural language processing today allows to process news and social media comments to detect signals of investors' confidence. We have explored the relationship between sentiment extracted from financial news and tweets and FTSE100 movements. We investigated the strength of the correlation between sentiment measures on a given day and market volatility and returns observed the next day. The findings suggest that there is evidence of c…
Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）；Indian Institute of Technology, Delhi（印度理工学院德里分校）
Sentiment analysis (SA) has become an extensive research area in recent years impacting diverse fields including ecommerce, consumer business, and politics, driven by increasing adoption and usage of social media platforms. It is challenging to extract topics and sentiments from unsupervised short texts emerging in such contexts, as they may contain figurative words, strident data, and co-existence of many possible meanings for a single word or phrase, all contributing to obtaining incorrect topics. Most prior research is based on a specific theme/rhetoric/focused-content on a clean dataset. I…
Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning
Academy for Engineering and Technology, Fudan University（复旦大学工程与技术学院）；Cognition and Intelligent Technology Laboratory（认知与智能技术实验室）；Institute of Metaverse & Intelligent Medicine, Fudan University（复旦大学元宇宙与智能医学研究院）；Jilin Provincial Key Laboratory of Intelligence Science and Engineering（吉林省智能科学与工程重点实验室）；Engineering Research Center of AI and Robotics, Ministry of Education（教育部人工智能与机器人工程研究中心）
ShanghaiTech University（上海科技大学）；Westlake Institute for Advanced Study（西湖高等研究院）；Westlake University（西湖大学）
Neural models have been investigated for sentiment classification over constituent trees. They learn phrase composition automatically by encoding tree structures but do not explicitly model sentiment composition, which requires to encode sentiment class labels. To this end, we investigate two formalisms with deep sentiment representations that capture sentiment subtype expressions by latent variables and Gaussian mixture vectors, respectively. Experiments on Stanford Sentiment Treebank (SST) show the effectiveness of sentiment grammar over vanilla neural encoders. Using ELMo embeddings, our me…
IBM Corporation（国际商业机器公司）；North Carolina State University（北卡罗来纳州立大学）
Opinionated text often involves attributes such as authorship and location that influence the sentiments expressed for different aspects. We posit that structural and semantic correspondence is both prevalent in opinionated text, especially when associated with attributes, and crucial in accurately revealing its latent aspect and sentiment structure. However, it is not recognized by existing approaches. We propose Trait, an unsupervised probabilistic model that discovers aspects and sentiments from text and associates them with different attributes. To this end, Trait infers and leverages stru…
Ruhr University Bochum（波鸿鲁尔大学）；Bucknell University（巴克内尔大学）
Traditional computational authorship attribution describes a classification task in a closed-set scenario. Given a finite set of candidate authors and corresponding labeled texts, the objective is to determine which of the authors has written another set of anonymous or disputed texts. In this work, we propose a probabilistic autoencoding framework to deal with this supervised classification task. More precisely, we are extending a variational autoencoder (VAE) with embedded Gaussian mixture model to a Student-$t$ mixture model. Autoencoders have had tremendous success in learning latent repre…
This paper introduces Latent Relational Analysis (LRA), a method for measuring relational similarity. LRA has potential applications in many areas, including information extraction, word sense disambiguation, machine translation, and information retrieval. Relational similarity is correspondence between relations, in contrast with attributional similarity, which is correspondence between attributes. When two words have a high degree of attributional similarity, we call them synonyms. When two pairs of words have a high degree of relational similarity, we say that their relations are analogous.…
This paper describes a large global dataset on people's discourse and responses to the COVID-19 pandemic over the Twitter platform. From 28 January 2020 to 1 June 2022, we collected and processed over 252 million Twitter posts from more than 29 million unique users using four keywords: "corona", "wuhan", "nCov" and "covid". Leveraging probabilistic topic modelling and pre-trained machine learning-based emotion recognition algorithms, we labelled each tweet with seventeen attributes, including a) ten binary attributes indicating the tweet's relevance (1) or irrelevance (0) to the top ten detect…
Due to the superior performance, large-scale pre-trained language models (PLMs) have been widely adopted in many aspects of human society. However, we still lack effective tools to understand the potential bias embedded in the black-box models. Recent advances in prompt tuning show the possibility to explore the internal mechanism of the PLMs. In this work, we propose two token-level sentiment tests: Sentiment Association Test (SAT) and Sentiment Shift Test (SST) which utilize the prompt as a probe to detect the latent bias in the PLMs. Our experiments on the collection of sentiment datasets s…
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；CIFAR（加拿大高级研究院）
Autoregressive language models are powerful and relatively easy to train. However, these models are usually trained without explicit conditioning labels and do not offer easy ways to control global aspects such as sentiment or topic during generation. Bowman & al. (2016) adapted the Variational Autoencoder (VAE) for natural language with the sequence-to-sequence architecture and claimed that the latent vector was able to capture such global features in an unsupervised manner. We question this claim. We measure which words benefit most from the latent information by decomposing the reconstructi…
Hong Kong University of Science and Technology（香港科技大学）；University of Southern California（南加州大学）
In this paper, we propose a variational approach to weakly supervised document-level multi-aspect sentiment classification. Instead of using user-generated ratings or annotations provided by domain experts, we use target-opinion word pairs as "supervision." These word pairs can be extracted by using dependency parsers and simple rules. Our objective is to predict an opinion word given a target word while our ultimate goal is to learn a sentiment polarity classifier to predict the sentiment polarity of each aspect given a document. By introducing a latent variable, i.e., the sentiment polarity,…
Text analysis of social media for sentiment, topic analysis, and other analysis depends initially on the selection of keywords and phrases that will be used to create the research corpora. However, keywords that researchers choose may occur infrequently, leading to errors that arise from using small samples. In this paper, we use the capacity for memorization, interpolation, and extrapolation of Transformer Language Models such as the GPT series to learn the linguistic behaviors of a subgroup within larger corpora of Yelp reviews. We then use prompt-based queries to generate synthetic text tha…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Arrive Bio（Arrive Bio（阿里夫生物））
Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to steer the model to generate a target sentence is already encoded within the model. Accordingly, we explore a different approach altogether: extracting latent vectors directly from pretrained language model decoders without fine-tuning. Experiments show that there exist steering vectors, which, when added to the hidden states of the language model, generate a t…
Evaluating Large Language Models Against Human Annotators in Latent Content Analysis: Sentiment, Political Leaning, Emotional Intensity, and Sarcasm
Institute for Artificial Intelligence Research and Development of Serbia（塞尔维亚人工智能研究与发展研究所）；University of Belgrade（贝尔格莱德大学）；Institute for Philosophy and Social Theory（哲学与社会理论研究所）；Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau (RPTU)（莱茵兰-普法尔茨州 Kaiserslautern-Landau 应用科技大学）；German Research Centre for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Vilnius Gediminas Technical University（维尔纽斯格迪米纳斯技术大学）；Drexel University（德雷塞尔大学）；University of Montenegro（黑山大学）；Faculty of Dramatic Arts（戏剧艺术学院）；University of Kragujevac（克拉古耶瓦茨大学）；Faculty of Engineering（工程学院）
