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

Helping each Other: A Framework for Customer-to-Customer Suggestion Mining using a Semi-supervised Deep Neural Network

Nov 01, 2018
Hitesh Golchha, Deepak Gupta, Asif Ekbal, Pushpak Bhattacharyya

Suggestion mining is increasingly becoming an important task along with sentiment analysis. In today's cyberspace world, people not only express their sentiments and dispositions towards some entities or services, but they also spend considerable time sharing their experiences and advice to fellow customers and the product/service providers with two-fold agenda: helping fellow customers who are likely to share a similar experience, and motivating the producer to bring specific changes in their offerings which would be more appreciated by the customers. In our current work, we propose a hybrid deep learning model to identify whether a review text contains any suggestion. The model employs semi-supervised learning to leverage the useful information from the large amount of unlabeled data. We evaluate the performance of our proposed model on a benchmark customer review dataset, comprising of the reviews of Hotel and Electronics domains. Our proposed approach shows the F-scores of 65.6% and 65.5% for the Hotel and Electronics review datasets, respectively. These performances are significantly better compared to the existing state-of-the-art system.

* To be appear in the proceedings of ICON 2018 

  Access Paper or Ask Questions

GeDi: Generative Discriminator Guided Sequence Generation

Sep 14, 2020
Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann, Nitish Shirish Keskar, Shafiq Joty, Richard Socher, Nazneen Fatema Rajani

Class-conditional language models (CC-LMs) can be used to generate natural language with specific attributes, such as style or sentiment, by conditioning on an attribute label, or control code. However, we find that these models struggle to control generation when applied to out-of-domain prompts or unseen control codes. To overcome these limitations, we propose generative discriminator (GeDi) guided contrastive generation, which uses CC-LMs as generative discriminators (GeDis) to efficiently guide generation from a (potentially much larger) LM towards a desired attribute. In our human evaluation experiments, we show that GeDis trained for sentiment control on movie reviews are able to control the tone of book text. We also demonstrate that GeDis are able to detoxify generation and control topic while maintaining the same level of linguistic acceptability as direct generation from GPT-2 (1.5B parameters). Lastly, we show that a GeDi trained on only 4 topics can generalize to new control codes from word embeddings, allowing it to guide generation towards wide array of topics.

  Access Paper or Ask Questions

Improving Multimodal fusion via Mutual Dependency Maximisation

Sep 09, 2021
Pierre Colombo, Emile Chapuis, Matthieu Labeau, Chloe Clavel

Multimodal sentiment analysis is a trending area of research, and the multimodal fusion is one of its most active topic. Acknowledging humans communicate through a variety of channels (i.e visual, acoustic, linguistic), multimodal systems aim at integrating different unimodal representations into a synthetic one. So far, a consequent effort has been made on developing complex architectures allowing the fusion of these modalities. However, such systems are mainly trained by minimising simple losses such as $L_1$ or cross-entropy. In this work, we investigate unexplored penalties and propose a set of new objectives that measure the dependency between modalities. We demonstrate that our new penalties lead to a consistent improvement (up to $4.3$ on accuracy) across a large variety of state-of-the-art models on two well-known sentiment analysis datasets: \texttt{CMU-MOSI} and \texttt{CMU-MOSEI}. Our method not only achieves a new SOTA on both datasets but also produces representations that are more robust to modality drops. Finally, a by-product of our methods includes a statistical network which can be used to interpret the high dimensional representations learnt by the model.

* EMNLP 2021 

  Access Paper or Ask Questions

Parallelizing Legendre Memory Unit Training

Feb 22, 2021
Narsimha Chilkuri, Chris Eliasmith

Recently, a new recurrent neural network (RNN) named the Legendre Memory Unit (LMU) was proposed and shown to achieve state-of-the-art performance on several benchmark datasets. Here we leverage the linear time-invariant (LTI) memory component of the LMU to construct a simplified variant that can be parallelized during training (and yet executed as an RNN during inference), thus overcoming a well known limitation of training RNNs on GPUs. We show that this reformulation that aids parallelizing, which can be applied generally to any deep network whose recurrent components are linear, makes training up to 200 times faster. Second, to validate its utility, we compare its performance against the original LMU and a variety of published LSTM and transformer networks on seven benchmarks, ranging from psMNIST to sentiment analysis to machine translation. We demonstrate that our models exhibit superior performance on all datasets, often using fewer parameters. For instance, our LMU sets a new state-of-the-art result on psMNIST, and uses half the parameters while outperforming DistilBERT and LSTM models on IMDB sentiment analysis.

  Access Paper or Ask Questions

Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction

Jan 07, 2020
Zhen Wu, Fei Zhao, Xin-Yu Dai, Shujian Huang, Jiajun Chen

Target-oriented opinion words extraction (TOWE) is a new subtask of ABSA, which aims to extract the corresponding opinion words for a given opinion target in a sentence. Recently, neural network methods have been applied to this task and achieve promising results. However, the difficulty of annotation causes the datasets of TOWE to be insufficient, which heavily limits the performance of neural models. By contrast, abundant review sentiment classification data are easily available at online review sites. These reviews contain substantial latent opinions information and semantic patterns. In this paper, we propose a novel model to transfer these opinions knowledge from resource-rich review sentiment classification datasets to low-resource task TOWE. To address the challenges in the transfer process, we design an effective transformation method to obtain latent opinions, then integrate them into TOWE. Extensive experimental results show that our model achieves better performance compared to other state-of-the-art methods and significantly outperforms the base model without transferring opinions knowledge. Further analysis validates the effectiveness of our model.

* Accepted by the 34th AAAI Conference on Artificial Intelligence (AAAI 2020) 

  Access Paper or Ask Questions

Opinion Mining in Online Reviews About Distance Education Programs

Jul 21, 2016
Janik Jaskolski, Fabian Siegberg, Thomas Tibroni, Philipp Cimiano, Roman Klinger

The popularity of distance education programs is increasing at a fast pace. En par with this development, online communication in fora, social media and reviewing platforms between students is increasing as well. Exploiting this information to support fellow students or institutions requires to extract the relevant opinions in order to automatically generate reports providing an overview of pros and cons of different distance education programs. We report on an experiment involving distance education experts with the goal to develop a dataset of reviews annotated with relevant categories and aspects in each category discussed in the specific review together with an indication of the sentiment. Based on this experiment, we present an approach to extract general categories and specific aspects under discussion in a review together with their sentiment. We frame this task as a multi-label hierarchical text classification problem and empirically investigate the performance of different classification architectures to couple the prediction of a category with the prediction of particular aspects in this category. We evaluate different architectures and show that a hierarchical approach leads to superior results in comparison to a flat model which makes decisions independently.

  Access Paper or Ask Questions

Biased or Not?: The Story of Two Search Engines

Dec 23, 2021
Gizem Gezici

Search engines can be considered as a gate to the world of WEB, and they also decide what we see for a given search query. Since many people are exposed to information through search engines, it is fair to expect that search engines should be neutral; i.e. the returned results must cover all the elements or aspects of the search topic, and they should be impartial where the results are returned based on relevance. However, the search engine results are based on many features and sophisticated algorithms where search neutrality is not necessarily the focal point. In this work we performed an empirical study on two popular search engines and analysed the search engine result pages for controversial topics such as abortion, medical marijuana, and gay marriage. Our analysis is based on the sentiment in search results to identify their viewpoint as conservative or liberal. We also propose three sentiment-based metrics to show the existence of bias as well as to compare viewpoints of the two search engines. Extensive experiments performed on controversial topics show that both search engines are biased, moreover they have the same kind of bias towards a given controversial topic.

  Access Paper or Ask Questions

Comparison of Classical Machine Learning Approaches on Bangla Textual Emotion Analysis

Jul 18, 2019
Md. Ataur Rahman, Md. Hanif Seddiqui

Detecting emotions from text is an extension of simple sentiment polarity detection. Instead of considering only positive or negative sentiments, emotions are conveyed using more tangible manner; thus, they can be expressed as many shades of gray. This paper manifests the results of our experimentation for fine-grained emotion analysis on Bangla text. We gathered and annotated a text corpus consisting of user comments from several Facebook groups regarding socio-economic and political issues, and we made efforts to extract the basic emotions (sadness, happiness, disgust, surprise, fear, anger) conveyed through these comments. Finally, we compared the results of the five most popular classical machine learning techniques namely Naive Bayes, Decision Tree, k-Nearest Neighbor (k-NN), Support Vector Machine (SVM) and K-Means Clustering with several combinations of features. Our best model (SVM with a non-linear radial-basis function (RBF) kernel) achieved an overall average accuracy score of 52.98% and an F1 score (macro) of 0.3324

  Access Paper or Ask Questions

Opinion Mining In Hindi Language: A Survey

Apr 19, 2014
Richa Sharma, Shweta Nigam, Rekha Jain

Opinions are very important in the life of human beings. These Opinions helped the humans to carry out the decisions. As the impact of the Web is increasing day by day, Web documents can be seen as a new source of opinion for human beings. Web contains a huge amount of information generated by the users through blogs, forum entries, and social networking websites and so on To analyze this large amount of information it is required to develop a method that automatically classifies the information available on the Web. This domain is called Sentiment Analysis and Opinion Mining. Opinion Mining or Sentiment Analysis is a natural language processing task that mine information from various text forms such as reviews, news, and blogs and classify them on the basis of their polarity as positive, negative or neutral. But, from the last few years, enormous increase has been seen in Hindi language on the Web. Research in opinion mining mostly carried out in English language but it is very important to perform the opinion mining in Hindi language also as large amount of information in Hindi is also available on the Web. This paper gives an overview of the work that has been done Hindi language.

* International Journal in Foundations of Computer Science & Technology (IJFCST) International Journal in Foundations of Computer Science & Technology (IJFCST), Vol.4, No.2, March 2014 

  Access Paper or Ask Questions

TextSETTR: Label-Free Text Style Extraction and Tunable Targeted Restyling

Oct 08, 2020
Parker Riley, Noah Constant, Mandy Guo, Girish Kumar, David Uthus, Zarana Parekh

We present a novel approach to the problem of text style transfer. Unlike previous approaches that use parallel or non-parallel labeled data, our technique removes the need for labels entirely, relying instead on the implicit connection in style between adjacent sentences in unlabeled text. We show that T5 (Raffel et al., 2019), a strong pretrained text-to-text model, can be adapted to extract a style vector from arbitrary text and use this vector to condition the decoder to perform style transfer. As the resulting learned style vector space encodes many facets of textual style, we recast transfers as "targeted restyling" vector operations that adjust specific attributes of the input text while preserving others. When trained over unlabeled Amazon reviews data, our resulting TextSETTR model is competitive on sentiment transfer, even when given only four exemplars of each class. Furthermore, we demonstrate that a single model trained on unlabeled Common Crawl data is capable of transferring along multiple dimensions including dialect, emotiveness, formality, politeness, and sentiment.

  Access Paper or Ask Questions