ParallelDots at SemEval-2019 Task 3: Domain Adaptation with feature embeddings for Contextual Emotion Analysis

Jain, Akansha; Aggarwal, Ishita; Singh, Ankit

doi:10.18653/v1/s19-2029

Cited by 6 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The stand-alone VADER includes a dedicated emoji lexicon that is omitted in the NLTK version. Some studies (Jain et al, 2019) show that an emoji can moderate the sentiment of a given tweet if the sentiment of an emoji is considered during training. Clearly, systems trained on emoji-bearing data can learn to consider them during prediction if their tokenization is handled properly and they are not discarded during preprocessing.…”

Section: Resultsmentioning

confidence: 99%

Assessing Emoji Use in Modern Text Processing Tools

Shoeb¹,

Melo²

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Emojis have become ubiquitous in digital communication, due to their visual appeal as well as their ability to vividly convey human emotion, among other factors. This also leads to an increased need for systems and tools to operate on text containing emojis. In this study, we assess this support by considering test sets of tweets with emojis, based on which we perform a series of experiments investigating the ability of prominent NLP and text processing tools to adequately process them. In particular, we consider tokenization, part-of-speech tagging, dependency parsing, as well as sentiment analysis. Our findings show that many systems still have notable shortcomings when operating on text containing emojis.

show abstract

Section: Resultsmentioning

confidence: 99%

Assessing Emoji Use in Modern Text Processing Tools

Shoeb¹,

Melo²

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…Finally, for revealing emotions of the complainants, ParallelDots Emotion Analysis AI API, which reveals basic emotions based on Ekman's (1999) theory of basic emotion, is employed. ParallelDots employs convolutional neural networks and provides numerical values ranging from 0.0 to 1.0 for the following emotions: happiness, sadness, anger, fear, excitement and boredom (Jain et al ., 2019). Since sentiment polarity only reveals the tone of complaint regarding being positive, negative and neutral, emotions are also employed for obtaining a deeper understanding of the nuances regarding the underlying tone of the complaints.…”

Section: Methodsmentioning

confidence: 99%

Online complaint handling: a text analytics-based classification framework

Yelkenci

Özdağoğlu

Ilter

2023

MIP

View full text Add to dashboard Cite

PurposeThis study aims to both identify content-based and interaction-based online consumer complaint types and predict complaint types according to the complaint magnitude rooted in complainants' personality traits, emotion, Twitter usage activity, as well as complaint's sentiment polarity, and interaction rate.Design/methodology/approachIn total, 297,000 complaint tweets were collected from Twitter, featuring over 220,000 consumer profiles and over 24 million user tweets. The obtained data were analyzed via two-step machine learning approach.FindingsThis study proposes a set of content and profile features that can be employed for determining complaint types and reveals the relationship between content features, profile features and online complaint type.Originality/valueThis study proposes a novel model for identifying types of online complaints, offering a set of content and profile features that can be used for predicting complaint type, and therefore introduces a flexible approach for enhancing online complaint management.

show abstract

“…From the number of tools available for text analysis, we find the usage of ParallelDots framework and their API functionalities from (Paralleldots, 2020) a proper fit to automatically identify the frequency and dominance of a variety of behavioural indicators in relevant messages. This tool utilizes models pretrained with machine learning techniques from (Jain, Aggarwal, & Singh, 2019) for the recognition of the well-known basic emotions from (Ekman, 1992) and (Plutchik & Kellerman, 1980). Although further details about the machine learning models are not provided in the systemś API documentation, we describe the list of five behavioural indicators and their confidence scores provided as category values which we consider in our analysis:…”

Section: Text Analyisis and User's Behavioural Indicatorsmentioning

confidence: 99%

Social Media Behaviour Analysis in Disaster-Response Messages of Floods and Heat Waves via Artificial Intelligence

Ponce-López¹,

Spataru²

2022

CIS

View full text Add to dashboard Cite

This paper analyses social media data in multiple disaster-related collections of floods and heat waves in the UK. The proposed method uses machine learning classifiers based on deep bidirectional neural networks trained on benchmark datasets of disaster responses and extreme events. The resulting models are applied to perform a qualitative analysis via topic inference in text data. We further analyse a set of behavioural indicators and match them with climate variables via decoding synoptical records to analyse thermal comfort. We highlight the advantages of aligning behavioural indicators along with climate variables to provide with 7 additional valuable information to be considered especially in different phases of a disaster and applicable to extreme weather periods. The positiveness of messages is around 8% for disaster, 1% for disaster and medical response, 7% for disaster and humanitarian related messages. This shows the reliability of such data for our case studies. We show the transferability of this approach to be applied to any social media data collection.

show abstract

ParallelDots at SemEval-2019 Task 3: Domain Adaptation with feature embeddings for Contextual Emotion Analysis

Cited by 6 publications

References 14 publications

Assessing Emoji Use in Modern Text Processing Tools

Assessing Emoji Use in Modern Text Processing Tools

Online complaint handling: a text analytics-based classification framework

Social Media Behaviour Analysis in Disaster-Response Messages of Floods and Heat Waves via Artificial Intelligence

Contact Info

Product

Resources

About