Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Sentiment": models, code, and papers

The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements

Jan 15, 2021
Lukas Stappen, Alice Baird, Lea Schumann, Björn Schuller

Truly real-life data presents a strong, but exciting challenge for sentiment and emotion research. The high variety of possible `in-the-wild' properties makes large datasets such as these indispensable with respect to building robust machine learning models. A sufficient quantity of data covering a deep variety in the challenges of each modality to force the exploratory analysis of the interplay of all modalities has not yet been made available in this context. In this contribution, we present MuSe-CaR, a first of its kind multimodal dataset. The data is publicly available as it recently served as the testing bed for the 1st Multimodal Sentiment Analysis Challenge, and focused on the tasks of emotion, emotion-target engagement, and trustworthiness recognition by means of comprehensively integrating the audio-visual and language modalities. Furthermore, we give a thorough overview of the dataset in terms of collection and annotation, including annotation tiers not used in this year's MuSe 2020. In addition, for one of the sub-challenges - predicting the level of trustworthiness - no participant outperformed the baseline model, and so we propose a simple, but highly efficient Multi-Head-Attention network that exceeds using multimodal fusion the baseline by around 0.2 CCC (almost 50 % improvement).


  Access Paper or Ask Questions

A Precisely Xtreme-Multi Channel Hybrid Approach For Roman Urdu Sentiment Analysis

Mar 11, 2020
Faiza Memood, Muhammad Usman Ghani, Muhammad Ali Ibrahim, Rehab Shehzadi, Muhammad Nabeel Asim

In order to accelerate the performance of various Natural Language Processing tasks for Roman Urdu, this paper for the very first time provides 3 neural word embeddings prepared using most widely used approaches namely Word2vec, FastText, and Glove. The integrity of generated neural word embeddings is evaluated using intrinsic and extrinsic evaluation approaches. Considering the lack of publicly available benchmark datasets, it provides a first-ever Roman Urdu dataset which consists of 3241 sentiments annotated against positive, negative and neutral classes. To provide benchmark baseline performance over the presented dataset, we adapt diverse machine learning (Support Vector Machine Logistic Regression, Naive Bayes), deep learning (convolutional neural network, recurrent neural network), and hybrid approaches. Effectiveness of generated neural word embeddings is evaluated by comparing the performance of machine and deep learning based methodologies using 7, and 5 distinct feature representation approaches respectively. Finally, it proposes a novel precisely extreme multi-channel hybrid methodology which outperforms state-of-the-art adapted machine and deep learning approaches by the figure of 9%, and 4% in terms of F1-score. Roman Urdu Sentiment Analysis, Pretrain word embeddings for Roman Urdu, Word2Vec, Glove, Fast-Text


  Access Paper or Ask Questions

Improved Twitter Sentiment Analysis Using Naive Bayes and Custom Language Model

Nov 10, 2017
Angela Lin

In the last couple decades, social network services like Twitter have generated large volumes of data about users and their interests, providing meaningful business intelligence so organizations can better understand and engage their customers. All businesses want to know who is promoting their products, who is complaining about them, and how are these opinions bringing or diminishing value to a company. Companies want to be able to identify their high-value customers and quantify the value each user brings. Many businesses use social media metrics to calculate the user contribution score, which enables them to quantify the value that influential users bring on social media, so the businesses can offer them more differentiated services. However, the score calculation can be refined to provide a better illustration of a user's contribution. Using Microsoft Azure as a case study, we conducted Twitter sentiment analysis to develop a machine learning classification model that identifies tweet contents and sentiments most illustrative of positive-value user contribution. Using data mining and AI-powered cognitive tools, we analyzed factors of social influence and specifically, promotional language in the developer community. Our predictive model was a combination of a traditional supervised machine learning algorithm and a custom-developed natural language model for identifying promotional tweets, that identifies a product-specific promotion on Twitter with a 90% accuracy rate.


  Access Paper or Ask Questions

Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis

Oct 26, 2021
Juhua Liu, Qihuang Zhong, Liang Ding, Hua Jin, Bo Du, Dacheng Tao

Aspect-based Sentiment Analysis (ABSA) aims to determine the sentiment polarity towards an aspect. Because of the expensive and limited labelled data, the pretraining strategy has become the de-facto standard for ABSA. However, there always exists severe domain shift between the pretraining and downstream ABSA datasets, hindering the effective knowledge transfer when directly finetuning and making the downstream task performs sub-optimal. To mitigate such domain shift, we introduce a unified alignment pretraining framework into the vanilla pretrain-finetune pipeline with both instance- and knowledge-level alignments. Specifically, we first devise a novel coarse-to-fine retrieval sampling approach to select target domain-related instances from the large-scale pretraining dataset, thus aligning the instances between pretraining and target domains (\textit{First Stage}). Then, we introduce a knowledge guidance-based strategy to further bridge the domain gap at the knowledge level. In practice, we formulate the model pretrained on the sampled instances into a knowledge guidance model and a learner model, respectively. On the target dataset, we design an on-the-fly teacher-student joint fine-tuning approach to progressively transfer the knowledge from the knowledge guidance model to the learner model (\textit{Second Stage}). Thereby, the learner model can maintain more domain-invariant knowledge when learning new knowledge from the target dataset. In the \textit{Third Stage,} the learner model is finetuned to better adapt its learned knowledge to the target dataset. Extensive experiments and analyses on several ABSA benchmarks demonstrate the effectiveness and universality of our proposed pretraining framework. Notably, our pretraining framework pushes several strong baseline models up to the new state-of-the-art records. We release our code and models.

* Under review 

  Access Paper or Ask Questions

[email protected] at SemEval-2020 Task 9: Generative Morphemes with an Attention Model for Sentiment Analysis in Code-Mixed Text

Jul 27, 2020
Koustava Goswami, Priya Rani, Bharathi Raja Chakravarthi, Theodorus Fransen, John P. McCrae

Code mixing is a common phenomena in multilingual societies where people switch from one language to another for various reasons. Recent advances in public communication over different social media sites have led to an increase in the frequency of code-mixed usage in written language. In this paper, we present the Generative Morphemes with Attention (GenMA) Model sentiment analysis system contributed to SemEval 2020 Task 9 SentiMix. The system aims to predict the sentiments of the given English-Hindi code-mixed tweets without using word-level language tags instead inferring this automatically using a morphological model. The system is based on a novel deep neural network (DNN) architecture, which has outperformed the baseline F1-score on the test data-set as well as the validation data-set. Our results can be found under the user name "koustava" on the "Sentimix Hindi English" page

* To be published in 14th International Workshop on Semantic Evaluation SemEval-2020 

  Access Paper or Ask Questions

A Novel Sentiment Analysis Engine for Preliminary Depression Status Estimation on Social Media

Nov 29, 2020
Sudhir Kumar Suman, Hrithwik Shalu, Lakshya A Agrawal, Archit Agrawal, Juned Kadiwala

Text sentiment analysis for preliminary depression status estimation of users on social media is a widely exercised and feasible method, However, the immense variety of users accessing the social media websites and their ample mix of vocabularies makes it difficult for commonly applied deep learning-based classifiers to perform. To add to the situation, the lack of adaptability of traditional supervised machine learning could hurt at many levels. We propose a cloud-based smartphone application, with a deep learning-based backend to primarily perform depression detection on Twitter social media. The backend model consists of a RoBERTa based siamese sentence classifier that compares a given tweet (Query) with a labeled set of tweets with known sentiment ( Standard Corpus ). The standard corpus is varied over time with expert opinion so as to improve the model's reliability. A psychologist ( with the patient's permission ) could leverage the application to assess the patient's depression status prior to counseling, which provides better insight into the mental health status of a patient. In addition, to the same, the psychologist could be referred to cases of similar characteristics, which could in turn help in more effective treatment. We evaluate our backend model after fine-tuning it on a publicly available dataset. The find tuned model is made to predict depression on a large set of tweet samples with random noise factors. The model achieved pinnacle results, with a testing accuracy of 87.23% and an AUC of 0.8621.


  Access Paper or Ask Questions

Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics

Jun 25, 2019
Niru Maheswaranathan, Alex Williams, Matthew D. Golub, Surya Ganguli, David Sussillo

Recurrent neural networks (RNNs) are a widely used tool for modeling sequential data, yet they are often treated as inscrutable black boxes. Given a trained recurrent network, we would like to reverse engineer it--to obtain a quantitative, interpretable description of how it solves a particular task. Even for simple tasks, a detailed understanding of how recurrent networks work, or a prescription for how to develop such an understanding, remains elusive. In this work, we use tools from dynamical systems analysis to reverse engineer recurrent networks trained to perform sentiment classification, a foundational natural language processing task. Given a trained network, we find fixed points of the recurrent dynamics and linearize the nonlinear system around these fixed points. Despite their theoretical capacity to implement complex, high-dimensional computations, we find that trained networks converge to highly interpretable, low-dimensional representations. In particular, the topological structure of the fixed points and corresponding linearized dynamics reveal an approximate line attractor within the RNN, which we can use to quantitatively understand how the RNN solves the sentiment analysis task. Finally, we find this mechanism present across RNN architectures (including LSTMs, GRUs, and vanilla RNNs) trained on multiple datasets, suggesting that our findings are not unique to a particular architecture or dataset. Overall, these results demonstrate that surprisingly universal and human interpretable computations can arise across a range of recurrent networks.


  Access Paper or Ask Questions

Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa -- A Large Romanian Sentiment Data Set

Jan 11, 2021
Anca Maria Tache, Mihaela Gaman, Radu Tudor Ionescu

Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools. In this paper, we introduce LaRoSeDa, a Large Romanian Sentiment Data Set, which is composed of 15,000 positive and negative reviews collected from one of the largest Romanian e-commerce platforms. We employ two sentiment classification methods as baselines for our new data set, one based on low-level features (character n-grams) and one based on high-level features (bag-of-word-embeddings generated by clustering word embeddings with k-means). As an additional contribution, we replace the k-means clustering algorithm with self-organizing maps (SOMs), obtaining better results because the generated clusters of word embeddings are closer to the Zipf's law distribution, which is known to govern natural language. We also demonstrate the generalization capacity of using SOMs for the clustering of word embeddings on another recently-introduced Romanian data set, for text categorization by topic.

* Accepted at EACL 2021 

  Access Paper or Ask Questions

Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis

Oct 16, 2020
Sunny Verma, Jiwei Wang, Zhefeng Ge, Rujia Shen, Fan Jin, Yang Wang, Fang Chen, Wei Liu

Multimodal sentiment analysis utilizes multiple heterogeneous modalities for sentiment classification. The recent multimodal fusion schemes customize LSTMs to discover intra-modal dynamics and design sophisticated attention mechanisms to discover the inter-modal dynamics from multimodal sequences. Although powerful, these schemes completely rely on attention mechanisms which is problematic due to two major drawbacks 1) deceptive attention masks, and 2) training dynamics. Nevertheless, strenuous efforts are required to optimize hyperparameters of these consolidate architectures, in particular their custom-designed LSTMs constrained by attention schemes. In this research, we first propose a common network to discover both intra-modal and inter-modal dynamics by utilizing basic LSTMs and tensor based convolution networks. We then propose unique networks to encapsulate temporal-granularity among the modalities which is essential while extracting information within asynchronous sequences. We then integrate these two kinds of information via a fusion layer and call our novel multimodal fusion scheme as Deep-HOSeq (Deep network with higher order Common and Unique Sequence information). The proposed Deep-HOSeq efficiently discovers all-important information from multimodal sequences and the effectiveness of utilizing both types of information is empirically demonstrated on CMU-MOSEI and CMU-MOSI benchmark datasets. The source code of our proposed Deep-HOSeq is and available at https://github.com/sverma88/Deep-HOSeq--ICDM-2020.

* Accepted at ICDM 2020 

  Access Paper or Ask Questions

Learning to Attend via Word-Aspect Associative Fusion for Aspect-based Sentiment Analysis

Dec 14, 2017
Yi Tay, Anh Tuan Luu, Siu Cheung Hui

Aspect-based sentiment analysis (ABSA) tries to predict the polarity of a given document with respect to a given aspect entity. While neural network architectures have been successful in predicting the overall polarity of sentences, aspect-specific sentiment analysis still remains as an open problem. In this paper, we propose a novel method for integrating aspect information into the neural model. More specifically, we incorporate aspect information into the neural model by modeling word-aspect relationships. Our novel model, \textit{Aspect Fusion LSTM} (AF-LSTM) learns to attend based on associative relationships between sentence words and aspect which allows our model to adaptively focus on the correct words given an aspect term. This ameliorates the flaws of other state-of-the-art models that utilize naive concatenations to model word-aspect similarity. Instead, our model adopts circular convolution and circular correlation to model the similarity between aspect and words and elegantly incorporates this within a differentiable neural attention framework. Finally, our model is end-to-end differentiable and highly related to convolution-correlation (holographic like) memories. Our proposed neural model achieves state-of-the-art performance on benchmark datasets, outperforming ATAE-LSTM by $4\%-5\%$ on average across multiple datasets.

* Accepted to AAAI2018 

  Access Paper or Ask Questions

<<
91
92
93
94
95
96
97
98
99
100
101
102
103
>>