SemEval-2014 Task 4: Aspect Based Sentiment Analysis

By Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar. 2014

1,897 citations recorded by the source corpus.

Sentiment analysis is increasingly viewed as a vital task both from an academic and a commercial standpoint. The majority of current approaches, however, attempt to detect the overall polarity of a sentence, paragraph, or text span, irrespective of the entities mentioned (e.g., laptops) and their aspects (e.g., battery, screen). SemEval2014 Task 4 aimed to foster research in the field of aspect-based sentiment analysis, where the goal is to identify the aspects of given target entities and the sentiment expressed for each aspect. The task provided datasets containing manually annotated reviews of restaurants and laptops, as well as a common evaluation procedure. It attracted 163 submissions from 32 teams.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bing Liu
2. Erik Cambria
3. Saif M. Mohammad
4. Lidong Bing
5. Philip S. Yu
6. Hu Xu
7. B. Liu
8. Lei Shu

In Natural Language Processing

1. Erik Cambria
2. Saif M. Mohammad
3. Zhiyuan Liu
4. Maosong Sun
5. Bing Liu
6. Xipeng Qiu
7. Jianfeng Gao
8. Mohit Bansal

Citations in the corpus

• Towards Interpretable Natural Language Understanding with Explanations as Latent Variables (2020, methodology): “We use two customer review datasets, Restaurant and Laptop, which are part of SemEval 2014 Task 4 [24] for the aspect-based sentiment classification task.”
• Attention-based LSTM for Aspect-level Sentiment Classification (2016, methodology): “We experiment on the dataset of SemEval 2014 Task 4 2 (Pontiki et al., 2014).”
• Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (2019, methodology): “We also evaluate our method on SemEval-2014 Task 4 (Pontiki et al., 2014) dataset 4 for aspect-based sentiment analysis.”
• SemEval-2015 Task 12: Aspect Based Sentiment Analysis (2015, background): “, PRICE) and their polarity only for restaurants (Pontiki et al., 2014).”
• Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021, methodology): “are made public from the SemEval ABSA challenge (Pontiki et al., 2014).”
• Multi-grained Attention Network for Aspect-Level Sentiment Classification (2018, background): “The first two are from the SemEval 2014 Task 41 (Pontiki et al., 2014), which contains the reviews in laptop and restaurants, respectively.”
• Train No Evil: Selective Masking for Task-guided Pre-training (2020, methodology): “We evaluate our method on two sentiment analysis tasks: MR (Pang and Lee, 2005) and SemEval14 task 4 restaurant and laptop datasets (Pontiki et al., 2014), using the model architecture of BERTBASE in Devlin et al.”
• Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings (2015, methodology): “Datasets: In our experiments, we use the two review datasets provided by the SemEval-2014 task 4: aspect-based sentiment analysis evaluation campaign (Pontiki et al., 2014), namely the Laptop and the Restaurant datasets.”
• Survey on Aspect-Level Sentiment Analysis (2016, methodology): “analysis [13], [14], providing a controlled evaluation methodology and shared data sets for all participants.”
• SemEval-2016 Task 5: Aspect Based Sentiment Analysis (2016, background): “…different research problems (Seki et al., 2007; Seki et al., 2008; Seki et al., 2010; Mitchell, 2013; Nakov et al., 2013; Rosenthal et al., 2014; Pontiki et al., 2014; Rosenthal et al., 2015; Ghosh et al., 2015; Pontiki et al., 2015; Moham-mad et al., 2016; Recupero and Cambria, 2014;…”
• Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (2020, methodology): “…is originally built by Dong et al. (2014), and the other four datasets (Lap14, Rest 14, Rest 15, Rest16) are respectively from SemEval 2014 task 4 (Pontiki et al., 2014), SemEval 2015 task 12 (Pontiki et al., 2015) and SemEval 2016 task 5 (Hercig et al., 2016), consisting of data from two…”
• Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review (2019, background): “infrequent (Rana et al., 2016). Others extracted OTE and ACD by exploiting opinion and target relations. Poria, Chaturvedi, Cambria, and Bisio (2016) and Piryani, Gupta, and Singh (2017) focused on rule-based linguistic patterns, including stop words and negation, etc.”
• Recurrent Attention Network on Memory for Aspect Sentiment Analysis (2017, methodology): “, “Certainly not the best sushi in New York, however, it is always fresh” (Pontiki et al., 2014).”