Abstract Since the SciCap dataset’s launch in 2021, the research community has made significant progress in generating captions for scientific figures in scholarly articles. In 2023, the first SciCap Challenge took place, inviting global teams to use an expanded SciCap dataset to develop models for captioning diverse figure types across various academic fields. At the same time, text generation models advanced quickly, with many powerful pre-trained large multimodal models (LMMs) emerging that showed impressive capabilities in various vision-and-language tasks. This paper presents an overview of the first SciCap Challenge and details the performance of various models on its data, capturing a snapshot of the field’s state. We found that professional editors overwhelmingly preferred figure captions generated by GPT-4V over those from all other models and even the original captions written by authors. Following this key finding, we conducted detailed analyses to answer this question: Have advanced LMMs solved the task of generating captions for scientific figures?

Wei-Hsin Yeh, Yu-An Su, Chih-Ning Chen, Yi-Hsueh Lin, Calvin Ku, Wenhsin Chiu, Min-Chun Hu, Lun-Wei Ku. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Fine-grained emotion classification (FEC) is a challenging task.Specifically, FEC needs to handle subtle nuance between labels, which can be complex and confusing.Most existing models only address text classification problem in the euclidean space, which we believe may not be the optimal solution as labels of close semantic (e.g., afraid and terrified) may not be differentiated in such space, which harms the performance.In this paper, we propose Hy-pEmo, a novel framework that can integrate hyperbolic embeddings to improve the FEC task.First, we learn label embeddings in the hyperbolic space to better capture their hierarchical structure, and then our model projects contextualized representations to the hyperbolic space to compute the distance between samples and labels.Experimental results show that incorporating such distance to weight cross entropy loss substantially improves the performance with significantly higher efficiency.We evaluate our proposed model on two benchmark datasets and found 4.8% relative improvement compared to the previous state of the art with 43.2% fewer parameters and 76.9% less training time.Code is available at https: //github.com/dinobby/HypEmo.

This work introduces a novel task, locationaware visual question generation (LocaVQG), which aims to generate engaging questions from data relevant to a particular geographical location.Specifically, we represent such location-aware information with surrounding images and a GPS coordinate.To tackle this task, we present a dataset generation pipeline that leverages GPT-4 to produce diverse and sophisticated questions.Then, we aim to learn a lightweight model that can address the Lo-caVQG task and fit on an edge device, such as a mobile phone.To this end, we propose a method which can reliably generate engaging questions from location-aware information.Our proposed method outperforms baselines regarding human evaluation (e.g., engagement, grounding, coherence) and automatic evaluation metrics (e.g., BERTScore, ROUGE-2).Moreover, we conduct extensive ablation studies to justify our proposed techniques for generating the dataset and solving the task.

Automatic identification of salient aspects from user reviews is especially useful for opinion analysis. There has been significant progress in utilizing weakly supervised approaches, which require only a small set of seed words for training aspect classifiers. However, there is always room for improvement. First, no weakly supervised approaches fully utilize latent hierarchies between words. Second, each seed word’s representation should have different latent semantics and be distinct when it represents a different aspect. In this paper we propose HDAE, a hyperbolic disentangled aspect extractor in which a hyperbolic aspect classifier captures words’ latent hierarchies, and an aspect-disentangled representation models the distinct latent semantics of each seed word. Compared to previous baselines, HDAE achieves average F1 performance gains of 18.2% and 24.1% on Amazon product review and restaurant review datasets, respectively. In addition, the embedding visualization experience demonstrates that HDAE is a more effective approach to leveraging seed words. An ablation study and a case study further attest the effectiveness of the proposed components.

Chi-Yang Hsu, Yun-Wei Chu, Vincent Chen, Kuan-Chieh Lo, Chacha Chen, Ting-Hao Huang, Lun-Wei Ku. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Generating engaging content has drawn much recent attention in the NLP community.Asking questions is a natural way to respond to photos and promote awareness.However, most answers to questions in traditional questionanswering (QA) datasets are factoids, which reduce individuals' willingness to answer.Furthermore, traditional visual question generation (VQG) confines the source data for question generation to single images, resulting in a limited ability to comprehend time-series information of the underlying event.In this paper, we propose generating engaging questions from multiple images.We present MVQG 1 , a new dataset, and establish a series of baselines, including both end-to-end and dual-stage architectures.Results show that building stories behind the image sequence enables models to generate engaging questions, which confirms our assumption that people typically construct a picture of the event in their minds before asking questions.These results open up an exciting challenge for visual-and-language models to implicitly construct a story behind a series of photos to allow for creativity and experience sharing and hence draw attention to downstream applications.How would you act if you found yourself in a room filled with cans of free drinks?Have you ever gone to beer tastings and where would that be at?How long did the cat lounge around in the book room?What would this cat sit on next?

Automated fact-checking systems have been proposed that quickly provide veracity prediction at scale to mitigate the negative influence of fake news on people and on public opinion. However, most studies focus on veracity classifiers of those systems, which merely predict the truthfulness of news articles. We posit that effective fact checking also relies on people's understanding of the predictions. In this paper, we propose elucidating fact-checking predictions using counterfactual explanations to help people understand why a specific piece of news was identified as fake.

We design and evaluate VICTOR, an easy-to-apply module on top of a recommender system to mitigate misinformation. VICTOR takes an elegant, implicit approach to deliver fake-news verifications, such that readers of fake news can continuously access more verified news articles about fake-news events without explicit correction. We frame fake-news intervention within VICTOR as a graph-based question-answering (QA) task, with Q as a fake-news article and A as the corresponding verified articles. Specifically, VICTOR adopts reinforcement learning: it first considers fake-news readers’ preferences supported by underlying news recommender systems and then directs their reading sequence towards the verified news articles. To verify the performance of VICTOR, we collect and organize VERI, a new dataset consisting of real-news articles, user browsing logs, and fake-real news pairs for a large number of misinformation events. We evaluate zero-shot and few-shot VICTOR on VERI to simulate the never-exposed-ever and seen-before conditions of users while reading a piece of fake news. Results demonstrate that compared to baselines, VICTOR proactively delivers 6% more verified articles with a diversity increase of 7.5% to over 68% of at-risk users who have been exposed to fake news. Moreover, we conduct a field user study in which 165 participants evaluated fake news articles. Participants in the VICTOR condition show better exposure rates, proposal rates, and click rates on verified news articles than those in the other two conditions. Altogether, our work demonstrates the potentials of VICTOR, i.e., combat fake news by delivering verified information implicitly.

Although many studies use the LIWC lexicon to show the existence of verbal leakage cues in lie detection datasets, none mention how verbal leakage cues are influenced by means of data collection, or the impact thereof on the performance of models.In this paper, we study verbal leakage cues to understand the effect of the data construction method on their significance, and examine the relationship between such cues and models' validity.The LIWC word-category dominance scores of seven lie detection datasets are used to show that audio statements and lie-based annotations indicate a greater number of strong verbal leakage cue categories.Moreover, we evaluate the validity of state-of-the-art lie detection models with cross-and in-dataset testing.Results show that in both types of testing, models trained on a dataset with more strong verbal leakage cue categories-as opposed to only a greater number of strong cues-yield superior results, suggesting that verbal leakage cues are a key factor for selecting lie detection datasets.

The use of crowdworkers in NLP research is growing rapidly, in tandem with the exponential increase in research production in machine learning and AI.Ethical discussion regarding the use of crowdworkers within the NLP research community is typically confined in scope to issues related to labor conditions such as fair pay.We draw attention to the lack of ethical considerations related to the various tasks performed by workers, including labeling, evaluation, and production.We find that the Final Rule, the common ethical framework used by researchers, did not anticipate the use of online crowdsourcing platforms for data collection, resulting in gaps between the spirit and practice of human-subjects ethics in NLP research.We enumerate common scenarios where crowdworkers performing NLP tasks are at risk of harm.We thus recommend that researchers evaluate these risks by considering the three ethical principles set up by the Belmont Report.We also clarify some common misconceptions regarding the Institutional Review Board (IRB) application.We hope this paper will serve to reopen the discussion within our community regarding the ethical use of crowdworkers.

There has been significant progress in the utilization of heterogeneous knowledge graphs (KG) as auxiliary information in recommendation systems. Reasoning over KG paths sheds light on the user's decision-making process. Previous methods focus on formulating this process as a multi-hop reasoning problem. However, without some form of guidance in the reasoning process, such a huge search space results in poor accuracy and little explanation diversity. In this paper, we propose UCPR, a user-centric path reasoning network that constantly guides the search from the aspect of user demand and enables explainable recommendations. In this network, a multi-view structure leverages not only local sequence reasoning information but also a panoramic view of the user's demand portfolio while inferring subsequent user decision-making steps. Experiments on five real-world benchmarks show UCPR is significantly more accurate than state-of-the-art methods. Besides, we show that the proposed model successfully identifies users' concerns and increases reason-ing diversity to enhance explainability

There has been significant progress in utilizing heterogeneous knowledge graphs (KGs) as auxiliary information in recommendation systems. However, existing KG-aware recommendation models rely solely on Euclidean space, neglecting hyperbolic space, which has already been shown to possess a superior ability to separate embed-dings by providing more "room". We propose a knowledge-based hyperbolic propagation framework (KBHP) which includes hyperbolic components for calculating the importance of KG attributes relative to achieve better knowledge propagation. In addition to the original relations in the knowledge graph, we propose a user purchase relation to better represent logical patterns in hyperbolic space, which bridges users and items for modeling user preference. Experiments on four real-world benchmarks show that KBHP is significantly more accurate than state-of-the-art models. We further visualize the generated embeddings to demonstrate that the proposed model successfully clusters attributes that are relevant to items and highlights those that contain useful information for the recommendation.

To address the increasingly significant issue of fake news, we develop a news reading platform in which we propose an implicit approach to reduce people's belief in fake news. Specifically, we leverage reinforcement learning to learn an intervention module on top of a recommender system (RS) such that the module is activated to replace RS to recommend news toward the verification once users touch the fake news. To examine the effect of the proposed method, we conduct a comprehensive evaluation with 89 human subjects and check the effective rate of change in belief but without their other limitations. Moreover, 84% participants indicate the proposed platform can help them defeat fake news. The demo video is available on YouTube https://youtu.be/wKI6nuXu_SM.

Visual dialogue systems need to understand dynamic visual scenes and comprehend semantics in order to converse with users. Constructing video dialogue systems is more challenging than traditional image dialogue systems because the large feature space of videos makes it difficult to capture semantic information. Furthermore, the dialogue system also needs to precisely answer users' question based on comprehensive understanding of the videos and the previous dialogue. In order to improve the performance of video dialogue system, we proposed an end-to-end recurrent cross-modality attention (ReCMA) model to answer a series of questions about a video from both visual and textual modality. The answer representation of the question is updated based on both visual representation and textual representation in each step of the reasoning process to have a better understanding of both modalities' information. We evaluate our method on the challenging DSTC7 video scene-aware dialog dataset and the proposed ReCMA achieves a relative 20.8% improvement over the baseline on CIDEr.

Stories are diverse and highly personalized, resulting in a large possible output space for story generation. Existing end-to-end approaches produce monotonous stories because they are limited to the vocabulary and knowledge in a single training dataset. This paper introduces KG-Story, a three-stage framework that allows the story generation model to take advantage of external Knowledge Graphs to produce interesting stories. KG-Story distills a set of representative words from the input prompts, enriches the word set by using external knowledge graphs, and finally generates stories based on the enriched word set. This distill-enrich-generate framework allows the use of external resources not only for the enrichment phase, but also for the distillation and generation phases. In this paper, we show the superiority of KG-Story for visual storytelling, where the input prompt is a sequence of five photos and the output is a short story. Per the human ranking evaluation, stories generated by KG-Story are on average ranked better than that of the state-of-the-art systems. Our code and output stories are available at https://github.com/zychen423/KE-VIST.

With the rapid proliferation of online media sources and published news, headlines have become increasingly important for attracting readers to news articles, since users may be overwhelmed with the massive information. In this paper, we generate inspired headlines that preserve the nature of news articles and catch the eye of the reader simultaneously. The task of inspired headline generation can be viewed as a specific form of Headline Generation (HG) task, with the emphasis on creating an attractive headline from a given news article. To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG). PORL-HG exploits the extractive-abstractive architecture with 1) Popular Topic Attention (PTA) for guiding the extractor to select the attractive sentence from the article and 2) a popularity predictor for guiding the abstractor to rewrite the attractive sentence. Moreover, since the sentence selection of the extractor is not differentiable, techniques of reinforcement learning (RL) are utilized to bridge the gap with rewards obtained from a popularity score predictor. Through quantitative and qualitative experiments, we show that the proposed PORL-HG significantly outperforms the state-of-the-art headline generation models in terms of attractiveness evaluated by both human (71.03%) and the predictor (at least 27.60%), while the faithfulness of PORL-HG is also comparable to the state-of-the-art generation model.

Many English-as-a-second language learners have trouble using near-synonym words (e.g., small vs.little; briefly vs.shortly) correctly, and often look for example sentences to learn how two nearly synonymous terms differ. Prior work uses hand-crafted scores to recommend sentences but has difficulty in adopting such scores to all the near-synonyms as near-synonyms differ in various ways. We notice that the helpfulness of the learning material would reflect on the learners’ performance. Thus, we propose the inference-based learner-like agent to mimic learner behavior and identify good learning materials by examining the agent’s performance. To enable the agent to behave like a learner, we leverage entailment modeling’s capability of inferring answers from the provided materials. Experimental results show that the proposed agent is equipped with good learner-like behavior to achieve the best performance in both fill-in-the-blank (FITB) and good example sentence selection tasks. We further conduct a classroom user study with college ESL learners. The results of the user study show that the proposed agent can find out example sentences that help students learn more easily and efficiently. Compared to other models, the proposed agent improves the score of more than 17% of students after learning.

Sarcasm detection is an important task in affective computing, requiring large amounts of labeled data.We introduce reactive supervision, a novel data collection method that utilizes the dynamics of online conversations to overcome the limitations of existing data collection techniques.We use the new method to create and release a first-of-its-kind large dataset of tweets with sarcasm perspective labels and new contextual features.The dataset is expected to advance sarcasm detection research.Our method can be adapted to other affective computing domains, thus opening up new research opportunities.

Researchers have begun to utilize heterogeneous knowledge graphs(KGs) as auxiliary information in recommendation systems to mitigate the cold start and sparsity issues. However, utilizing a graph neural network (GNN) to capture information in KG and further apply in RS is still problematic as it is unable to see each item's properties from multiple perspectives. To address these issues, we propose the multi-view item network (MVIN), a GNN-based recommendation model that provides superior recommendations by describing items from a unique mixed view from user and entity angles. MVIN learns item representations from both the user view and the entity view. From the user view, user-oriented modules score and aggregate features to make recommendations from a personalized perspective constructed according to KG entities which incorporates user click information. From the entity view, the mixing layer contrasts layer-wise GCN information to further obtain comprehensive features from internal entity-entity interactions in the KG. We evaluate MVIN on three real-world datasets: MovieLens-1M (ML-1M), LFM-1b 2015 (LFM-1b), and Amazon-Book (AZ-book). Results show that MVIN significantly outperforms state-of-the-art methods on these three datasets. Besides, from user-view cases, we find that MVIN indeed captures entities that attract users. Figures further illustrate that mixing layers in a heterogeneous KG plays a vital role in neighborhood information aggregation.

As deep learning models are getting popular, upgrading the retrieval-based content recommendation system to the learning-based system is highly demanded. However, efficiency is a critical issue. For article recommendation, an effective neural network which generates a good representation of the article content could prove useful. Hence, we propose PGA-Recommender, a phrase-guided article recommendation model which mimics the process of human behavior - first browsing, then guided by key phrases, and finally aggregating the gleaned information. As this can be performed independently offline, it is thus compatible with current commercial retrieval-based (keyword-based) article recommender systems. A total of six months of real logs - from Apr 2017 to Sep 2017 - were used for experiments. Results show that PGA-Recommender outperforms different state-of-the-art schemes including session-, collaborative filter-, and content-based recommendation models. Moreover, it suggests a diverse mix of articles while maintaining superior performance in terms of both click and view predictions. The results of A/B tests show that simply using the backward version of PGA-Recommender yields 40% greater click-through rates as compared to the retrieval-based system when deployed to a language of which we have zero knowledge.

In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. The user initiates the process by uploading a sequence of photos. Dixit first extracts text terms from each photo which describe the objects (e.g., boy, bike) or actions (e.g., sleep) in the photo, and then allows the user to add new terms or remove existing terms. Dixit then generates a short story based on these terms. Behind the scenes, Dixit uses an LSTM-based model trained on image caption data and FrameNet to distill terms from each image, and utilizes a transformer decoder to compose a context-coherent story. Users change images or terms iteratively with Dixit to create the most ideal story. Dixit also allows users to manually edit and rate stories. The proposed procedure opens up possibilities for interpretable and controllable visual storytelling, allowing users to understand the story formation rationale and to intervene in the generation process.

We present Exam Keeper, a tool to measure the availability of answers to exam questions for ESL students. Exam Keeper targets two major sources of answers: the web, and apps. ESL teachers can use it to estimate which questions are easily answered by information on the web or by using automatic question answering systems, which should help teachers avoid such questions on their exams or homework to prevent students from misusing technology. The demo video is available at https://youtu.be/rgq0UXOkb8o 1

Recently chatbots have been widely deployed in social network messengers. To make these chatbots more human, we present EmotionPush, the first social spoken-language private dialog dataset containing instant message logs and the unique read event logs, containing a total of 162,031 message logs and their corresponding read logs of real private conversations on Facebook Messenger. We ensure data privacy by masking all the named entities with a code composed by their type and an unique ID. In addition, we take care of the debug need by releasing messages partially by their original words and partially in the form of word embeddings. In addition, with this dataset, we propose the emotion classification task and a novel response-time prediction task to enhance the humanity of chatbots. We establish strong baselines for these two tasks. Experiment results show that EmotionPush helps to achieve over 90% accuracy for major emotion classification and 89% accuracy for response time prediction. We expect to enable chatbots to know when to respond and what message to send to encourage user responses.

Web post and user stance labeling is challenging not only because of the informality and variation in language on the Web but also because of the lack of labeled data on fast-emerging new topics-even the labeled data we do have are usually heavily skewed. In this paper, we propose a joint user-post approach for stance labeling to mitigate the latter two difficulties. In labeling post stance, the proposed approach considers post content as well as posting and liking behavior, which involves users. Sentiment analysis is applied to posts to acquire their initial stance, and then the post and user stance are updated iteratively with correlated posting-related actions. The whole process works with limited labeled data, which solves the first problem. We use real interaction between authors and readers for stance labeling. Experimental results show that the proposed approach not only substantially improves content-based post stance labeling, but also yields better performance for the minor stance class, which solves the second problem.

To learn more knowledge, enabling transitivity is a vital step for lexical inference. However, most of the lexical inference models with good performance are for nouns or noun phrases, which cannot be directly applied to the inference on events or states. In this paper, we construct the largest Chinese verb lexical inference dataset containing 18,029 verb pairs, where for each pair one of four inference relations are annotated. We further build a probabilistic soft logic (PSL) model to infer verb lexicons using the logic language. With PSL, we easily enable transitivity in two layers, the observed layer and the feature layer, which are included in the knowledge base. We further discuss the effect of transitives within and between these layers. Results show the performance of the proposed PSL model can be improved at least 3.5% (relative) when the transitivity is enabled. Furthermore, experiments show that enabling transitivity in the observed layer benefits the most.

The rapid growth of web source has changed language learning behavior. More and more people utilized web sources instead of paper books. However, the problem now is that it is overwhelming to find useful information. In addition, when considering using different words, good example sentences demonstrating nuance among words are extremely helpful but learners can hardly find them as most web dictionaries contain explanations and examples for only a single word. To solve the problem, we proposed a system called GiveMeExample which can automatically search for the best example sentences of a group of confusing words. The proposed system learns the word usage model for each word in the confusing word group and a universal difficulty model for all sentences, in order to propose simple but clear example sentences for learners. Experiments show that the proposed approach can really provide the most useful example sentences for understanding confusing words. GiveMeExample is available at http://givemeexample.com/GiveMeExample.

Lexical inference problem is a significant component of some recent core AI and NLP research problems like machine reading and textual entailment. In this paper, we propose method utilizing the Probabilistic Soft Logic (PSL) model for Chinese lexical inference. The proposed PSL model not only can integrate two complementary traditional methods, i.e., the lexical-knowledge-based method and the distributional probabilistic method, but also can optimize the lexical inference network in a global view by the transitivity property of entailment relations. We build a large domain specific verb inference corpus containing 18,029 verb pairs with gold inference labels from math world problems. A five-folded experiment is performed. Results show that the proposed PSL model greatly outperforms our baseline.

Most neural network models for document classification on social media focus on text information to the neglect of other information on these platforms. In this paper, we classify post stance on social media channels and develop UTCNN, a neural network model that incorporates user tastes, topic tastes, and user comments on posts. UTCNN not only works on social media texts, but also analyzes texts in forums and message boards. Experiments performed on Chinese Facebook data and English online debate forum data show that UTCNN achieves a 0.755 macro average f-score for supportive, neutral, and unsupportive stance classes on Facebook data, which is significantly better than models in which either user, topic, or comment information is withheld. This model design greatly mitigates the lack of data for the minor class. In addition, UTCNN yields a 0.842 accuracy on English online debate forum data, which also significantly outperforms results from previous work, showing that UTCNN performs well regardless of language or platform.

Language learners' limited lexical knowledge leads to imprecise wording. This is especially true when they attempt to express their emotions. Many learners rely heavily on the traditional thesaurus. Unfortunately, this fails to provide appropriate suggestions for lexical choices. To better aid English-as-a-second-language learners with word choices, we propose RESOLVE, which provides ranked synonyms of emotion words based on contextual information. RESOLVE suggests precise emotion words regarding the events in the relevant context. Patterns are learned to capture emotion events, and various factors are considered in the scoring function for ranking emotion words. We also describe an online writing system developed using RESOLVE and evaluate its effectiveness for learning assistance with a writing task. Experimental results showed that RESOLVE yielded a superior performance on NDCG@5 which significantly outperformed both PMI and SVM approaches, and offered better suggestions than Roget's Thesaurus and PIGAI (an online automated essay scoring system). Moreover, when applying it to the writing task, students' appropriateness with emotion words was 30 percent improved. Less-proficient learners benefited more from RESOLVE than highly-proficient learners. Post-tests also showed that after using RESOLVE, less-proficient learners' ability to use emotion words approached that of highly-proficient learners. RESOLVE thus enables learners to use precise emotion words.

Abstract We present CopeOpi, an opinion‐analysis system, which extracts from the Web opinions about specific targets, summarizes the polarity and strength of these opinions, and tracks opinion variations over time. Objects that yield similar opinion tendencies over a certain time period may be correlated due to the latent causal events. CopeOpi discovers relationships among objects based on their opinion‐tracking plots and collocations. Event bursts are detected from the tracking plots, and the strength of opinion relationships is determined by the coverage of these plots. To evaluate opinion mining, we use the NTCIR corpus annotated with opinion information at sentence and document levels. CopeOpi achieves sentence‐ and document‐level f‐measures of 62% and 74%. For relationship discovery, we collected 1.3M economics‐related documents from 93 Web sources over 22 months, and analyzed collocation‐based, opinion‐based, and hybrid models. We consider as correlated company pairs that demonstrate similar stock‐price variations, and selected these as the gold standard for evaluation. Results show that opinion‐based and collocation‐based models complement each other, and that integrated models perform the best. The top 25, 50, and 100 pairs discovered achieve precision rates of 1, 0.92, and 0.79, respectively.

Abstract Documents discussing public affairs, common themes, interesting products, and so on, are reported and distributed on the Web. Positive and negative opinions embedded in documents are useful references and feedbacks for governments to improve their services, for companies to market their products, and for customers to purchase their objects. Web opinion mining aims to extract, summarize, and track various aspects of subjective information on the Web. Mining subjective information enables traditional information retrieval (IR) systems to retrieve more data from human viewpoints and provide information with finer granularity. Opinion extraction identifies opinion holders, extracts the relevant opinion sentences, and decides their polarities. Opinion summarization recognizes the major events embedded in documents and summarizes the supportive and the nonsupportive evidence. Opinion tracking captures subjective information from various genres and monitors the developments of opinions from spatial and temporal dimensions. To demonstrate and evaluate the proposed opinion mining algorithms, news and bloggers' articles are adopted. Documents in the evaluation corpora are tagged in different granularities from words, sentences to documents. In the experiments, positive and negative sentiment words and their weights are mined on the basis of Chinese word structures. The f‐measure is 73.18% and 63.75% for verbs and nouns, respectively. Utilizing the sentiment words mined together with topical words, we achieve f‐measure 62.16% at the sentence level and 74.37% at the document level.

No abstract available.