2020

Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research

Poria, Soujanya, Hazarika, Devamanyu, Majumder, Navonil et al.

Understand

Sentiment analysis as a field has come a long way since it was first introduced as a task nearly 20 years ago.

It has widespread commercial applications in various domains like marketing, risk management, market research, and politics, to name a few.
Given its saturation in specific subtasks -- such as sentiment polarity classification -- and datasets, there is an underlying perception that this field has reached its maturity.
In this article, we discuss this perception by pointing out the shortcomings and under-explored, yet key aspects of this field that are necessary to attain true sentiment understanding.

Built on

Reducing sentiment bias in language models via counterfactual evaluation
Original
Huang, P., Zhang, H., Jiang, R., Stanforth, R., Welbl, J., Rae, J., Maini, V., Yogatama, D., and Kohli, P · 1911
Earlier work this paper cites.
Feeling and thinking: Preferences need no inferences
Zajonc, R. B · 1980
Earlier work this paper cites.
Thoughts on the relations between emotion and cognition
Lazarus, R. S · 1982
Earlier work this paper cites.
Test of the mention theory of irony
Jorgensen, J., Miller, G. A., and Sperber, D · 1984
Earlier work this paper cites.
Generating natural language under pragmatic constraints
Hovy, E · 1987
Earlier work this paper cites.
Tracking point of view in narrative
Wiebe, J. M · 1994
Earlier work this paper cites.
Wordnet: A lexical database for english
Miller, G. A · 1995
Earlier work this paper cites.
Using Language
Clark, H. H · 1996
Earlier work this paper cites.
Predicting the semantic orientation of adjectives
Hatzivassiloglou, V. and McKeown, K. R · 1997
Earlier work this paper cites.
Development and use of a gold-standard data set for subjectivity classifications
Wiebe, J. M., Bruce, R. F., and O’Hara, T. P · 1999
Earlier work this paper cites.
Effects of adjective orientation and gradability on sentence subjectivity
Hatzivassiloglou, V. and Wiebe, J. M · 2000
Earlier work this paper cites.
How emotions work: The social functions of emotional expression in negotiations
Morris, M. W. and Keltner, D · 2000
Earlier work this paper cites.
Learning subjective adjectives from corpora
Wiebe, J · 2000
Earlier work this paper cites.
An operational system for detecting and tracking opinions in on-line discussion
Tong, R. M · 2001
Earlier work this paper cites.
Mining product reputations on the web
Morinaga, S., Yamanishi, K., Tateishi, K., and Fukushima, T · 2002
Earlier work this paper cites.
Thumbs up?: sentiment classification using machine learning techniques
Pang, B., Lee, L., and Vaithyanathan, S · 2002
Earlier work this paper cites.
Srilm-an extensible language modeling toolkit
Stolcke, A · 2002
Earlier work this paper cites.
Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews
Turney, P. D · 2002
Earlier work this paper cites.
Learning from labeled and unlabeled data with label propagation
Zhu, X. and Ghahramani, Z · 2002
Earlier work this paper cites.
A neural probabilistic language model
Bengio, Y., Ducharme, R., Vincent, P., and Jauvin, C · 2003
Earlier work this paper cites.
Appraisal processes in emotion , pp. 572–595
Ellsworth, P. C. and Scherer, K. R · 2003
Earlier work this paper cites.
Sentiment analysis: Capturing favorability using natural language processing
Nasukawa, T. and Yi, J · 2003
Earlier work this paper cites.
Towards answering opinion questions: Separating facts from opinions and identifying the polarity of opinion sentences
Yu, H. and Hatzivassiloglou, V · 2003
Earlier work this paper cites.
Mining and summarizing customer reviews
Hu, M. and Liu, B · 2004
Earlier work this paper cites.
Determining the sentiment of opinions
Kim, S. and Hovy, E. H · 2004
Earlier work this paper cites.
A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts
Pang, B. and Lee, L · 2004
Earlier work this paper cites.
The effects of affective interventions in human–computer interaction
Partala, T. and Surakka, V · 2004
Earlier work this paper cites.
The empathic companion: A character-based interface that addresses users’affective states
Prendinger, H. and Ishizuka, M · 2005
Earlier work this paper cites.
Recognizing contextual polarity in phrase-level sentiment analysis
Wilson, T., Wiebe, J., and Hoffmann, P · 2005
Earlier work this paper cites.
Joint extraction of entities and relations for opinion recognition
Choi, Y., Breck, E., and Cardie, C · 2006
Earlier work this paper cites.
SENTIWORDNET: A publicly available lexical resource for opinion mining
Esuli, A. and Sebastiani, F · 2006
Earlier work this paper cites.
Extracting opinions, opinion holders, and topics expressed in online news media text
Kim, S.-M. and Hovy, E · 2006
Earlier work this paper cites.
Opinion extraction, summarization and tracking in news and blog corpora
Ku, L., Liang, Y., and Chen, H · 2006
Earlier work this paper cites.
Contextual valence shifters
Polanyi, L. and Zaenen, A · 2006
Earlier work this paper cites.
Word sense and subjectivity
Wiebe, J. and Mihalcea, R · 2006
Earlier work this paper cites.
Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification
Blitzer, J., Dredze, M., and Pereira, F · 2007
Earlier work this paper cites.
Personage: Personality generation for dialogue
Mairesse, F. and Walker, M · 2007
Earlier work this paper cites.
Topic sentiment mixture: modeling facets and opinions in weblogs
Mei, Q., Ling, X., Wondra, M., Su, H., and Zhai, C · 2007
Earlier work this paper cites.
Sentiment composition
Moilanen, K. and Pulman, S · 2007
Earlier work this paper cites.
IEMOCAP: interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., and Narayanan, S. S · 2008
Earlier work this paper cites.
The sound of sarcasm
Cheang, H. S. and Pell, M. D · 2008
Earlier work this paper cites.
Learning with compositional semantics as structural inference for subsentential sentiment analysis
Choi, Y. and Cardie, C · 2008
Earlier work this paper cites.
Towards building a competitive opinion summarization system: Challenges and keys
Lloret, E., Balahur, A., Palomar, M., and Montoyo, A · 2009
Earlier work this paper cites.
Delta TFIDF: an improved feature space for sentiment analysis
Martineau, J. and Finin, T · 2009
Earlier work this paper cites.
Adapting naive bayes to domain adaptation for sentiment analysis
Tan, S., Cheng, X., Wang, Y., and Xu, H · 2009
Earlier work this paper cites.
Prosodic contrasts in ironic speech
Bryant, G. A · 2010
Earlier work this paper cites.
Semi-supervised recognition of sarcastic sentences in twitter and amazon
Davidov, D., Tsur, O., and Rappoport, A · 2010
Earlier work this paper cites.
Emotional inertia and psychological maladjustment
Kuppens, P., Allen, N. B., and Sheeber, L. B · 2010
Earlier work this paper cites.
Sentiment analysis and subjectivity
Liu, B · 2010
Earlier work this paper cites.
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černockỳ, J., and Khudanpur, S · 2010
Earlier work this paper cites.
Opinion digger: an unsupervised opinion miner from unstructured product reviews
Moghaddam, S. and Ester, M · 2010
Earlier work this paper cites.
Emotions evoked by common words and phrases: Using Mechanical Turk to create an emotion lexicon
Mohammad, S. and Turney, P · 2010
Earlier work this paper cites.
Dependency tree-based sentiment classification using crfs with hidden variables
Nakagawa, T., Inui, K., and Kurohashi, S · 2010
Earlier work this paper cites.
Cross-domain sentiment classification via spectral feature alignment
Pan, S. J., Ni, X., Sun, J., Yang, Q., and Chen, Z · 2010
Earlier work this paper cites.
United we stand: Improving sentiment analysis by joining machine learning and rule based methods
Rentoumi, V., Petrakis, S., Klenner, M., Vouros, G. A., and Karkaletsis, V · 2010
Earlier work this paper cites.
ICWSM - A great catchy name: Semi-supervised recognition of sarcastic sentences in online product reviews
Tsur, O., Davidov, D., and Rappoport, A · 2010
Earlier work this paper cites.
The viability of web-derived polarity lexicons
Velikovich, L., Blair-Goldensohn, S., Hannan, K., and McDonald, R. T · 2010
Earlier work this paper cites.
Bridging domains using world wide knowledge for transfer learning
Xiang, E. W., Cao, B., Hu, D. H., and Yang, Q · 2010
Earlier work this paper cites.
Sentiment classification based on supervised latent n-gram analysis
Bespalov, D., Bai, B., Qi, Y., and Shokoufandeh, A · 2011
Earlier work this paper cites.
Natural language processing (almost) from scratch
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., and Kuksa, P · 2011
Earlier work this paper cites.
Domain adaptation for large-scale sentiment classification: A deep learning approach
Glorot, X., Bordes, A., and Bengio, Y · 2011
Earlier work this paper cites.
Identifying sarcasm in twitter: A closer look
González-Ibáñez, R. I., Muresan, S., and Wacholder, N · 2011
Earlier work this paper cites.
Identifying sarcasm in twitter: A closer look
González-Ibáñez, R. I., Muresan, S., and Wacholder, N · 2011
Earlier work this paper cites.
Automatically extracting polarity-bearing topics for cross-domain sentiment classification
He, Y., Lin, C., and Alani, H · 2011
Earlier work this paper cites.
A pattern-based model for generating text to express emotion
Keshtkar, F. and Inkpen, D · 2011
Earlier work this paper cites.
Twitter sentiment analysis: The good the bad and the omg!
Kouloumpis, E., Wilson, T., and Moore, J. D · 2011
Earlier work this paper cites.
Learning word vectors for sentiment analysis
Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., and Potts, C · 2011
Earlier work this paper cites.
Exploring feature definition and selection for sentiment classifiers
Mejova, Y. and Srinivasan, P · 2011
Earlier work this paper cites.
Opinion word expansion and target extraction through double propagation
Qiu, G., Liu, B., Bu, J., and Chen, C · 2011
Earlier work this paper cites.
Lexicon-based methods for sentiment analysis
Taboada, M., Brooke, J., Tofiloski, M., Voll, K. D., and Stede, M · 2011
Earlier work this paper cites.
Context and intonation in the perception of sarcasm
Woodland, J. and Voyer, D · 2011
Earlier work this paper cites.
Conflict, criticism, or confidence: An empirical examination of the gender gap in wikipedia contributions
Collier, B. and Bear, J · 2012
Earlier work this paper cites.
Sentiment Analysis and Opinion Mining
Liu, B · 2012
Earlier work this paper cites.
A survey of opinion mining and sentiment analysis
Liu, B. and Zhang, L · 2012
Earlier work this paper cites.
Lstm neural networks for language modeling
Sundermeyer, M., Schlüter, R., and Ney, H · 2012
Earlier work this paper cites.
Baselines and bigrams: Simple, good sentiment and topic classification
Wang, S. I. and Manning, C. D · 2012
Earlier work this paper cites.
Probase: A probabilistic taxonomy for text understanding
Wu, W., Li, H., Wang, H., and Zhu, K · 2012
Earlier work this paper cites.
Lost in translation: viability of machine translation for cross language sentiment analysis
Balamurali, A., Khapra, M. M., and Bhattacharyya, P · 2013
Earlier work this paper cites.
Predicting and eliciting addressee’s emotion in online dialogue
Hasegawa, T., Kaji, N., Yoshinaga, N., and Toyoda, M · 2013
Earlier work this paper cites.
Learning whom to trust with MACE
Hovy, D., Berg-Kirkpatrick, T., Vaswani, A., and Hovy, E. H · 2013
Earlier work this paper cites.

Similar

Re-embedding words
Labutov, I. and Lipson, H · 2013
Cited alongside, same era.
The geography of happiness: Connecting twitter sentiment and expression, demographics, and objective characteristics of place
Original
Mitchell, L., Harris, K. D., Frank, M. R., Dodds, P. S., and Danforth, C. M · 2013
Cited alongside, same era.
Crowdsourcing a word-emotion association lexicon
Mohammad, S. and Turney, P. D · 2013
Cited alongside, same era.
Semeval-2013 task 2: Sentiment analysis in twitter
Nakov, P., Rosenthal, S., Kozareva, Z., Stoyanov, V., Ritter, A., and Wilson, T · 2013
Cited alongside, same era.
Sarcasm as contrast between a positive sentiment and negative situation
Riloff, E., Qadir, A., Surve, P., Silva, L. D., Gilbert, N., and Huang, R · 2013
Cited alongside, same era.
Recursive deep models for semantic compositionality over a sentiment treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., and Potts, C · 2013
Cited alongside, same era.
Automatic domain-specific sentiment lexicon generation with label propagation
Tai, Y. and Kao, H · 2013
Cited alongside, same era.
Exploring demographic language variations to improve multilingual sentiment analysis in social media
Volkova, S., Wilson, T., and Yarowsky, D · 2013
Cited alongside, same era.
Joint inference for fine-grained opinion extraction
Yang, B. and Cardie, C · 2013
Cited alongside, same era.
Building sentiment lexicons for all major languages
Chen, Y. and Skiena, S · 2014
Cited alongside, same era.
Sentiment propagation via implicature constraints
Deng, L. and Wiebe, J · 2014
Cited alongside, same era.
Joint inference and disambiguation of implicit sentiments via implicature constraints
Deng, L., Wiebe, J., and Choi, Y · 2014
Cited alongside, same era.

Then

Dyadic memory networks for aspect-based sentiment analysis
Tay, Y., Tuan, L. A., and Hui, S. C · 2017
Later among the works it cites.
Attention is all you need
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I · 2017
Later among the works it cites.
Tensor fusion network for multimodal sentiment analysis
Zadeh, A., Chen, M., Poria, S., Cambria, E., and Morency, L.-P · 2017
Later among the works it cites.
Towards automatic generation of product reviews from aspect-sentiment scores
Zang, H. and Wan, X · 2017
Later among the works it cites.
Domain adaptation with adversarial training and graph embeddings
Alam, F., Joty, S. R., and Imran, M · 2018
Later among the works it cites.
Affective neural response generation
Asghar, N., Poupart, P., Hoey, J., Jiang, X., and Mou, L · 2018
Later among the works it cites.
Adversarial deep averaging networks for cross-lingual sentiment classification
Chen, X., Sun, Y., Athiwaratkun, B., Cardie, C., and Weinberger, K. Q · 2018
Later among the works it cites.
Sarcasm analysis using conversation context
Ghosh, D., Fabbri, A. R., and Muresan, S · 2018
Later among the works it cites.
CASCADE: contextual sarcasm detection in online discussion forums
Hazarika, D., Poria, S., Gorantla, S., Cambria, E., Zimmermann, R., and Mihalcea, R · 2018
Later among the works it cites.
ICON: interactive conversational memory network for multimodal emotion detection
Hazarika, D., Poria, S., Mihalcea, R., Cambria, E., and Zimmermann, R · 2018
Later among the works it cites.
Modeling inter-aspect dependencies for aspect-based sentiment analysis
Hazarika, D., Poria, S., Vij, P., Krishnamurthy, G., Cambria, E., and Zimmermann, R · 2018
Later among the works it cites.
Conversational memory network for emotion recognition in dyadic dialogue videos
Hazarika, D., Poria, S., Zadeh, A., Cambria, E., Morency, L., and Zimmermann, R · 2018
Later among the works it cites.
Universal language model fine-tuning for text classification
Howard, J. and Ruder, S · 2018
Later among the works it cites.
Sarcasm target identification: Dataset and an introductory approach
Joshi, A., Goel, P., Bhattacharyya, P., and Carman, M. J · 2018
Later among the works it cites.
Examining gender and race bias in two hundred sentiment analysis systems
Kiritchenko, S. and Mohammad, S · 2018
Later among the works it cites.
Delete, retrieve, generate: a simple approach to sentiment and style transfer
Li, J., Jia, R., He, H., and Liang, P · 2018
Later among the works it cites.
Modeling sentiment association in discourse for humor recognition
Liu, L., Zhang, D., and Song, W · 2018
Later among the works it cites.
Eliciting positive emotion through affect-sensitive dialogue response generation: A neural network approach
Lubis, N., Sakti, S., Yoshino, K., and Nakamura, S · 2018
Later among the works it cites.
Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM
Ma, Y., Peng, H., and Cambria, E · 2018
Later among the works it cites.
Deep contextualized word representations
Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., and Zettlemoyer, L · 2018
Later among the works it cites.
Domain adapted word embeddings for improved sentiment classification
Sarma, P. K., Liang, Y., and Sethares, B · 2018
Later among the works it cites.
Identifying transferable information across domains for cross-domain sentiment classification
Sharma, R., Bhattacharyya, P., Dandapat, S., and Bhatt, H. S · 2018
Later among the works it cites.
Learning domain-sensitive and sentiment-aware word embeddings
Shi, B., Fu, Z., Bing, L., and Lam, W · 2018
Later among the works it cites.
Reasoning with sarcasm by reading in-between
Tay, Y., Luu, A. T., Hui, S. C., and Su, J · 2018
Later among the works it cites.
Attentive gated lexicon reader with contrastive contextual co-attention for sentiment classification
Tay, Y., Luu, A. T., Hui, S. C., and Su, J · 2018
Later among the works it cites.
Learning sentiment composition from sentiment lexicons
Toledo-Ronen, O., Bar-Haim, R., Halfon, A., Jochim, C., Menczel, A., Aharonov, R., and Slonim, N · 2018
Later among the works it cites.
Sentigan: Generating sentimental texts via mixture adversarial networks
Wang, K. and Wan, X · 2018
Later among the works it cites.
Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph
Zadeh, A., Liang, P. P., Poria, S., Cambria, E., and Morency, L · 2018
Later among the works it cites.
Adversarial multiple source domain adaptation
Zhao, H., Zhang, S., Wu, G., Moura, J. M. F., Costeira, J. P., and Gordon, G. J · 2018
Later among the works it cites.
Gender bias in coreference resolution: Evaluation and debiasing methods
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., and Chang, K.-W · 2018
Later among the works it cites.
Learning gender-neutral word embeddings
Zhao, J., Zhou, Y., Li, Z., Wang, W., and Chang, K.-W · 2018
Later among the works it cites.
Emotional chatting machine: Emotional conversation generation with internal and external memory
Zhou, H., Huang, M., Zhang, T., Zhu, X., and Liu, B · 2018
Later among the works it cites.
Pivot based language modeling for improved neural domain adaptation
Ziser, Y. and Reichart, R · 2018
Later among the works it cites.
An ensemble of humour, sarcasm, and hate speechfor sentiment classification in online reviews
Badlani, R., Asnani, N., and Rai, M · 2019
Later among the works it cites.
Evaluating the underlying gender bias in contextualized word embeddings
Basta, C., Costa-jussà, M. R., and Casas, N · 2019
Later among the works it cites.
Comet: Commonsense transformers for automatic knowledge graph construction
Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., and Choi, Y · 2019
Later among the works it cites.
Towards multimodal sarcasm detection (an _obviously_ perfect paper)
Castro, S., Hazarika, D., Pérez-Rosas, V., Zimmermann, R., Mihalcea, R., and Poria, S · 2019
Later among the works it cites.
BERT: pre-training of deep bidirectional transformers for language understanding
Devlin, J., Chang, M., Lee, K., and Toutanova, K · 2019
Later among the works it cites.
Inducing document structure for aspect-based summarization
Frermann, L. and Klementiev, A · 2019
Later among the works it cites.
Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them
Gonen, H. and Goldberg, Y · 2019
Later among the works it cites.
Towards automated emotional conversation generation with implicit and explicit affective strategy
Gu, X., Xu, W., and Li, S · 2019
Later among the works it cites.
Sentiment analysis using unlabeled email data
Hag Ali, R. S. and El Gayar, N · 2019
Later among the works it cites.
UR-FUNNY: A multimodal language dataset for understanding humor
Hasan, M. K., Rahman, W., Zadeh, A. B., Zhong, J., Tanveer, M. I., Morency, L., and Hoque, M. E · 2019
Later among the works it cites.
Aspect-based sentiment analysis using BERT
Hoang, M., Bihorac, O. A., and Rouces, J · 2019
Later among the works it cites.
ANA at semeval-2019 task 3: Contextual emotion detection in conversations through hierarchical lstms and BERT
Huang, C., Trabelsi, A., and Zaïane, O. R · 2019
Later among the works it cites.
Disentangled representation learning for non-parallel text style transfer
John, V., Mou, L., Bahuleyan, H., and Vechtomova, O · 2019
Later among the works it cites.
Shallow domain adaptive embeddings for sentiment analysis
K Sarma, P., Liang, Y., and Sethares, W · 2019
Later among the works it cites.
Gender-preserving debiasing for pre-trained word embeddings
Kaneko, M. and Bollegala, D · 2019
Later among the works it cites.
An adversarial approach to high-quality, sentiment-controlled neural dialogue generation
Original
Kong, X., Li, B., Neubig, G., Hovy, E., and Yang, Y · 2019
Later among the works it cites.
Measuring bias in contextualized word representations
Kurita, K., Vyas, N., Pareek, A., Black, A. W., and Tsvetkov, Y · 2019
Later among the works it cites.
De-mixing sentiment from code-mixed text
Lal, Y. K., Kumar, V., Dhar, M., Shrivastava, M., and Koehn, P · 2019
Later among the works it cites.
A unified model for opinion target extraction and target sentiment prediction
Li, X., Bing, L., Li, P., and Lam, W · 2019
Later among the works it cites.
Roberta: A robustly optimized BERT pretraining approach
Original
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V · 2019
Later among the works it cites.
DOER: dual cross-shared RNN for aspect term-polarity co-extraction
Luo, H., Li, T., Liu, B., and Zhang, J · 2019
Later among the works it cites.
Dialoguernn: An attentive RNN for emotion detection in conversations
Majumder, N., Poria, S., Hazarika, D., Mihalcea, R., Gelbukh, A. F., and Cambria, E · 2019
Later among the works it cites.
Storytelling from structured data and knowledge graphs : An NLG perspective
Mishra, A., Laha, A., Sankaranarayanan, K., Jain, P., and Krishnan, S · 2019
Later among the works it cites.
A modular architecture for unsupervised sarcasm generation
Mishra, A., Tater, T., and Sankaranarayanan, K · 2019
Later among the works it cites.
Fine-grained sentiment classification using BERT
Original
Munikar, M., Shakya, S., and Shrestha, A · 2019
Later among the works it cites.
isarcasm: A dataset of intended sarcasm
Original
Oprea, S. and Magdy, W · 2019
Later among the works it cites.
Emotionally-aware chatbots: A survey
Original
Pamungkas, E. W · 2019
Later among the works it cites.
A deep-learning framework to detect sarcasm targets
Patro, J., Bansal, S., and Mukherjee, A · 2019
Later among the works it cites.
MELD: A multimodal multi-party dataset for emotion recognition in conversations
Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., and Mihalcea, R · 2019
Later among the works it cites.
End-to-end joint opinion role labeling with BERT
Quan, W., Zhang, J., and Hu, X. T · 2019
Later among the works it cites.
Exploring the limits of transfer learning with a unified text-to-text transformer
Original
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., and Liu, P. J · 2019
Later among the works it cites.
Gender bias in pretrained Swedish embeddings
Sahlgren, M. and Olsson, F · 2019
Later among the works it cites.
Sentiment classification using document embeddings trained with cosine similarity
Thongtan, T. and Phienthrakul, T · 2019
Later among the works it cites.
Unsupervised data augmentation
Original
Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., and Le, Q. V · 2019
Later among the works it cites.
Enhancing opinion role labeling with semantic-aware word representations from semantic role labeling
Zhang, M., Liang, P., and Fu, G · 2019
Later among the works it cites.
Gender bias in contextualized word embeddings
Zhao, J., Wang, T., Yatskar, M., Cotterell, R., Ordonez, V., and Chang, K.-W · 2019
Later among the works it cites.
Investigating gender bias in bert, 2020
Bhardwaj, R., Majumder, N., and Poria, S · 2020
Closest in time.
Senticnet 6: Ensemble application of symbolic and subsymbolic AI for sentiment analysis
Cambria, E., Li, Y., Xing, F. Z., Poria, S., and Kwok, K · 2020
Closest in time.
Rˆ3: Reverse, retrieve, and rank for sarcasm generation with commonsense knowledge
Chakrabarty, T., Ghosh, D., Muresan, S., and Peng, N · 2020
Closest in time.
Minority positive sampling for switching points - an anecdote for the code-mixing language modelling
Guptha, V., Chatterjee, A., Chopra, P., and Das, A · 2020
Closest in time.
MISA: modality-invariant and -specific representations for multimodal sentiment analysis
Hazarika, D., Zimmermann, R., and Poria, S · 2020
Closest in time.
Adversarial training for aspect-based sentiment analysis with BERT
Original
Karimi, A., Rossi, L., Prati, A., and Full, K · 2020
Closest in time.
Nurse is closer to woman than surgeon? mitigating gender-biased proximities in word embeddings
Kumar, V., Bhotia, T. S., and Chakraborty, T · 2020
Closest in time.
A survey on empathetic dialogue systems
Ma, Y., Nguyen, K. L., Xing, F. Z., and Cambria, E · 2020
Closest in time.
Improving aspect-level sentiment analysis with aspect extraction
Original
Majumder, N., Bhardwaj, R., Poria, S., Zadeh, A., Gelbukh, A. F., Hussain, A., and Morency, L · 2020
Closest in time.
A primer in bertology: What we know about how BERT works
Original
Rogers, A., Kovaleva, O., and Rumshisky, A · 2020
Closest in time.
Is it great or terrible? preserving sentiment in neural machine translation of arabic reviews
Original
Saadany, H. and Orasan, C · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…