Personalized review summarization is a challenging task in recommender systems, which aims to generate condensed and readable summaries for product reviews. Recently, some methods propose to adopt the sentiment signals of reviews to enhance the review summarization. However, most previous works only share the semantic features of reviews via preliminary multi-task learning, while ignoring the rich personalized information of users and products, which is crucial to both sentiment identification and comprehensive review summarization. In this paper, we propose a sentiment-aware review summarization method with an elaborately designed multi-task fine-tuning framework to make full use of personalized information of users and products effectively based on Pretrained Language Models (PLMs). We first denote two types of personalized information including IDs and historical summaries to indicate their identification and semantics information respectively. Subsequently, we propose to incorporate the IDs of the user/product into the PLMs-based encoder to learn the personalized representations of input reviews and their historical summaries in a fine-tuning way. Based on this, an auxiliary context-aware review sentiment classification task and a further sentiment-guided personalized review summarization task are jointly learned. Specifically, the sentiment representation of input review is used to identify relevant historical summaries, which are then treated as additional semantic context features to enhance the summary generation process. Extensive experimental results show our approach could generate sentiment-consistent summaries and outperforms many competitive baselines on both review summarization and sentiment classification tasks.

Expert finding aims at seeking potential users to answer new questions in Community Question Answering (CQA) websites. Most existing methods focus on designing matching frameworks between questions and experts, and rely on negative sampling technology for model training. However, sampling would lose lots of useful information about experts and questions, and make these sampling-based methods suffer the bias and non-robust issues, which may lead to an insufficient matching performance for expert findings. In this paper, we propose a novel Efficient Non-sampling Expert Finding model, named ENEF, which could learn accurate representations of questions and experts from whole training data. In our approach, we adopt a rather basic question encoder and a simple matching framework, then an efficient whole-data optimization method is elaborately designed to learn the model parameters without negative sampling with rather a low space and time complexity. Extensive experimental results on four real-world CQA datasets demonstrate that our model ENEF could achieve better performance and faster training efficiency than existing state-of-the-art expert finding methods.

Expert Finding is an important task in Community Question Answering (CQA) platforms, which could help route questions to potential expertise users to answer. The key is to model the question content and experts based on their historical answered questions accurately. Recently Pretrained Language Models (PLMs, e.g., Bert) have shown superior text modeling ability and have been used in expert finding preliminary. However, most PLMs-based models focus on the corpus or document granularity during pretraining, which is inconsistent with the downstream expert modeling and finding task. In this paper, we propose an expert-level pretraining language model named ExpertBert, aiming to model questions, experts as well as question-expert matching effectively in a pretraining manner. In our approach, we aggregate the historical answered questions of an expert as the expert-specific input.Besides, we integrate the target question into the input and design a label-augmented Masked Language Model (MLM) task to further capture the matching pattern between question and experts, which makes the pretraining objectives that more closely resemble the downstream expert finding task. Experimental results and detailed analysis on real-world CQA datasets demonstrate the effectiveness of our ExpertBert.

The increasing use of micro-blogging as a marketing tool has increased research attention on usage and business value of enterprise micro-blogging. Based on research on information system (IS) usage and resource-based view (RBV) theory, this study develops a model to reveal the mechanism of business value creation of enterprise micro-blogging. The model consists of metrics on micro-blogging usage, micro-blogging operational performance, marketing capability, and firm performance. Questionnaires were distributed to firms that use micro-blogging. This study collects 241 valid responses for empirical analysis. The results suggest that the use of enterprise micro-blogging improves operational performance of enterprise micro-blogging directly and indirectly by increasing marketing capability, while operational performance of enterprise micro-blogging significantly affects firm performance. This study extends the stream of research that combines IS usage and RBV theory.