SemEval-2015 Task 12: Aspect Based Sentiment Analysis

By Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Suresh Manandhar, Ion Androutsopoulos. International Workshop on Semantic Evaluation, 2015

1,066 citations recorded by the source corpus.

SemEval-2015 Task 12, a continuation of SemEval-2014 Task 4, aimed to foster research beyond sentenceor text-level sentiment classification towards Aspect Based Sentiment Analysis. The goal is to identify opinions expressed about specific entities (e.g., laptops) and their aspects (e.g., price). The task provided manually annotated reviews in three domains (restaurants, laptops and hotels), and a common evaluation procedure. It attracted 93 submissions from 16 teams.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/4e1c3d61ae3135a9f040125b787b2f145be5beb9

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

Citations in the corpus

Aspect Sentiment Quad Prediction as Paraphrase Generation (2021, methodology): “Dataset We build the ASQP datasets based on SemEval Shared Challenges (Pontiki et al., 2015, 2016).”
New word analogy corpus for exploring embeddings of Czech words (2016, methodology): “Word representations made by these methods have been successfully adapted on variety of core NLP task such as Named Entity Recognition [7,8], Part-of-speech Tagging [9], Sentiment Analysis [10], and others.”
Survey on Aspect-Level Sentiment Analysis (2016, methodology): “analysis [13], [14], providing a controlled evaluation methodology and shared data sets for all participants.”
Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review (2019, background): “3 SemEval 2015 (Pontiki et al., 2015) Laptop (EN): 450 reviews (2500 sentences) XML tag of {E#A, polarity} <sentence id="1004293:0"> <text> Judging from previous posts this used to be a good place, but not any longer.”
Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, neutral): “, positive, negative or neutral) of different aspects in the same sentence [2, 3].”
Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks (2019, methodology): “…posts, while the other four (L AP 14, R EST 14, R EST 15, R EST 16) are respectively from SemEval 2014 task 4 (Pontiki et al., 2014), SemEval 2015 task 12 (Pontiki et al., 2015) and SemEval 2016 task 5 (Pontiki et al., 2016), consisting of data from two categories, i.e. laptop and restaurant.”
Aspect-Based Sentiment Analysis using BERT (2019, methodology): “ABSA as a research topic gained special traction during SemEval-2014 (Pontiki et al., 2014) workshop, where it was ﬁrst introduced as Task 4 and reappeared in the SemEval-2015 (Pontiki et al., 2015) and SemEval-2016 (Pontiki et al., 2016) workshops.”
A Unified Model for Opinion Target Extraction and Target Sentiment Prediction (2018, background): “Note that as deﬁned by the task (Pontiki 2014; Pontiki 2015; Pontiki 2016), an opinion target should always co-occur with opinion words, thus, the words close to the opinion words are more likely to be target words and we obtain additional supervision signals for reﬁning boundary information based…”
Position-Aware Tagging for Aspect Sentiment Triplet Extraction (2020, methodology): “Such datasets were all created based on the datasets originally released by Se-mEval (Pontiki et al., 2014, 2015, 2016).”
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (2020, methodology): “, 2014), SemEval 2015 task 12 (Pontiki et al., 2015) and SemEval 2016 task 5 (Hercig et al.”
SemEval-2016 Task 6: Detecting Stance in Tweets (2016, background): “See Pontiki et al. (2014), Pontiki et al. (2015), and Kiritchenko et al. (2014a) for tasks and systems on aspect based sentiment analysis, where the goal is to determine sentiment towards aspects of a product such as speed of processor and screen resolution of a cell phone.”
Stance and Sentiment in Tweets (2016, methodology): “We refer the reader to SemEval proceedings for related work on ABSA [Pontiki et al. 2015; Pontiki et al. 2014].”
SemEval-2016 Task 5: Aspect Based Sentiment Analysis (2016, methodology): “(Pontiki et al., 2015), were adapted for the other languages by using appropriate stopword lists and to-kenization functions.”