Goto

Collaborating Authors

 Discourse & Dialogue


Exploiting Rich Textual User-Product Context for Improving Sentiment Analysis

arXiv.org Artificial Intelligence

User and product information associated with a review is useful for sentiment polarity prediction. Typical approaches incorporating such information focus on modeling users and products as implicitly learned representation vectors. Most do not exploit the potential of historical reviews, or those that currently do require unnecessary modifications to model architecture or do not make full use of user/product associations. The contribution of this work is twofold: i) a method to explicitly employ historical reviews belonging to the same user/product to initialize representations, and ii) efficient incorporation of textual associations between users and products via a user-product cross-context module. Experiments on IMDb, Yelp-2013 and Yelp-2014 benchmarks show that our approach substantially outperforms previous state-of-the-art. Since we employ BERT-base as the encoder, we additionally provide experiments in which our approach performs well with Span-BERT and Longformer. Furthermore, experiments where the reviews of each user/product in the training data are downsampled demonstrate the effectiveness of our approach under a low-resource setting.


Impact of Sentiment Analysis in Fake Review Detection

arXiv.org Artificial Intelligence

Fake review identification is an important topic and has gained the interest of experts all around the world. Identifying fake reviews is challenging for researchers, and there are several primary challenges to fake review detection. We propose developing an initial research paper for investigating fake reviews by using sentiment analysis. Ten research papers are identified that show fake reviews, and they discuss currently available solutions for predicting or detecting fake reviews. They also show the distribution of fake and truthful reviews through the analysis of sentiment. We summarize and compare previous studies related to fake reviews. We highlight the most significant challenges in the sentiment evaluation process and demonstrate that there is a significant impact on sentiment scores used to identify fake feedback.


How AI-driven sentiment analysis can enhance employee satisfaction

#artificialintelligence

Check out all the on-demand sessions from the Intelligent Security Summit here. With tech talent in short supply, companies are desperate to hold onto top performers. However, many are losing ground. Employees are sticking around for much shorter periods than they used to. Sentiment analysis combined with artificial intelligence (AI) is being harnessed to help companies in a number of ways: Discovering how employees feel about their work environment, how effective they feel training and skill development initiatives are, and what their concerns are, and how to spot danger signs, identify signs of burnout, identify indicators of job dissatisfaction, and prevent employees from jumping ship rivals.


Utilizing distilBert transformer model for sentiment classification of COVID-19's Persian open-text responses

arXiv.org Artificial Intelligence

The COVID-19 pandemic has caused drastic alternations in human's life in all aspects. The government's laws in this regard affected the lifestyle of all people. Due to this fact studying about the sentiment of individuals is important to be aware of the future impacts of the coming pandemics. To contribute to this aim, we proposed a NLP (Natural Language Processing) model to analyze open-text answers in a survey in Persian and detect positive and negative feelings of the people in Iran. In this study, a distilBert transformer model was applied to take on this task. We deployed three approaches to perform comparison, and our best model could gain accuracy: 0.824, Precision: 0.824, Recall: 0.798 and F1score: 0.804.


Sentiment Analysis on Encrypted Data with Homomorphic Encryption - KDnuggets

#artificialintelligence

It is well-known that a sentiment analysis model determines whether a text is positive, negative, or neutral. However, this process typically requires access to unencrypted text, which can pose privacy concerns. Homomorphic encryption is a type of encryption that allows for computation on encrypted data without needing to decrypt it first. This makes it well-suited for applications where user's personal and potentially sensitive data is at risk (e.g. This blog post uses the Concrete-ML library, allowing data scientists to use machine learning models in fully homomorphic encryption (FHE) settings without any prior knowledge of cryptography.


Multi-task Learning for Cross-Lingual Sentiment Analysis

arXiv.org Artificial Intelligence

This paper presents a cross-lingual sentiment analysis of news articles using zero-shot and few-shot learning. The study aims to classify the Croatian news articles with positive, negative, and neutral sentiments using the Slovene dataset. The system is based on a trilingual BERT-based model trained in three languages: English, Slovene, Croatian. The paper analyses different setups using datasets in two languages and proposes a simple multi-task model to perform sentiment classification. The evaluation is performed using the few-shot and zero-shot scenarios in single-task and multi-task experiments for Croatian and Slovene.


MCP: Self-supervised Pre-training for Personalized Chatbots with Multi-level Contrastive Sampling

arXiv.org Artificial Intelligence

Personalized chatbots focus on endowing the chatbots with a consistent personality to behave like real users and further act as personal assistants. Previous studies have explored generating implicit user profiles from the user's dialogue history for building personalized chatbots. However, these studies only use the response generation loss to train the entire model, thus it is prone to suffer from the problem of data sparsity. Besides, they overemphasize the final generated response's quality while ignoring the correlations and fusions between the user's dialogue history, leading to rough data representations and performance degradation. To tackle these problems, we propose a self-supervised learning framework MCP for capturing better representations from users' dialogue history for personalized chatbots. Specifically, we apply contrastive sampling methods to leverage the supervised signals hidden in user dialog history, and generate the pre-training samples for enhancing the model. We design three pre-training tasks based on three types of contrastive pairs from user dialogue history, namely response pairs, sequence augmentation pairs, and user pairs. We pre-train the utterance encoder and the history encoder towards the contrastive objectives and use these pre-trained encoders for generating user profiles while personalized response generation. Experimental results on two real-world datasets show a significant improvement in our proposed model MCP compared with the existing methods.


Twitter Sentiment Analysis with Hugging Face

#artificialintelligence

Sentiment analysis is a type of NLP that aims to label data according to its sentiments, such as positive, negative, and neutral. This analysis helps companies understand how their customers feel about their products or services or identify trends in public opinion about a particular topic. For example, a company like Audi can learn whether people like the colors of its new car by examining Twitter shares like the image below. With the developing technology, it is now much easier to express all kinds of emotions, feelings, and thoughts through social networking sites. Social media scraping is the process of extracting data from social media platforms.


Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access

arXiv.org Artificial Intelligence

To alleviate the problem of structured databases' limited coverage, recent task-oriented dialogue systems incorporate external unstructured knowledge to guide the generation of system responses. However, these usually use word or sentence level similarities to detect the relevant knowledge context, which only partially capture the topical level relevance. In this paper, we examine how to better integrate topical information in knowledge grounded task-oriented dialogue and propose ``Topic-Aware Response Generation'' (TARG), an end-to-end response generation model. TARG incorporates multiple topic-aware attention mechanisms to derive the importance weighting scheme over dialogue utterances and external knowledge sources towards a better understanding of the dialogue history. Experimental results indicate that TARG achieves state-of-the-art performance in knowledge selection and response generation, outperforming previous state-of-the-art by 3.2, 3.6, and 4.2 points in EM, F1 and BLEU-4 respectively on Doc2Dial, and performing comparably with previous work on DSTC9; both being knowledge-grounded task-oriented dialogue datasets.


Routine Outcome Monitoring in Psychotherapy Treatment using Sentiment-Topic Modelling Approach

arXiv.org Artificial Intelligence

Despite the importance of emphasizing the right psychotherapy treatment for an individual patient, assessing the outcome of the therapy session is equally crucial. Evidence showed that continuous monitoring patient's progress can significantly improve the therapy outcomes to an expected change. By monitoring the outcome, the patient's progress can be tracked closely to help clinicians identify patients who are not progressing in the treatment. These monitoring can help the clinician to consider any necessary actions for the patient's treatment as early as possible, e.g., recommend different types of treatment, or adjust the style of approach. Currently, the evaluation system is based on the clinical-rated and self-report questionnaires that measure patients' progress pre- and post-treatment. While outcome monitoring tends to improve the therapy outcomes, however, there are many challenges in the current method, e.g. time and financial burden for administering questionnaires, scoring and analysing the results. Therefore, a computational method for measuring and monitoring patient progress over the course of treatment is needed, in order to enhance the likelihood of positive treatment outcome. Moreover, this computational method could potentially lead to an inexpensive monitoring tool to evaluate patients' progress in clinical care that could be administered by a wider range of health-care professionals.