Abstract This research holds significance for advancing financial forecasting methodologies by shifting the focus from traditional sentiment analysis of individual tweets to exploring intricate semantic relationships within news tweets from top-followed news channels on Twitter. Addressing a notable research gap in financial forecasting, often dominated by sentiment analysis, our study endeavors to fill the void left by the underexplored intricate relationships within news entities and their dynamic semantic evolution. Motivated by the inherent challenges in predicting the random walk behavior of stock prices, we contend that incorporating longitudinal data derived from the semantic relationships between news entities can enhance the accuracy of stock market forecasts. The study pioneers a twelve-year exploration, encompassing data from 55 leading news channels on Twitter, boasting a collective following of 714 million users. The approach employs natural language processing (NLP) to extract two million unique entities, whose semantics are analyzed through complex network analysis, laying the foundation for the forecasting model. Finally, this research introduces a model linked to the dynamic semantic structure of news flow. The predictive model considers the impact of exogenous variables influenced by the evolving relationships among news entities. The results offer a proof of concept, highlighting the potential of utilizing dynamic semantic relationships among news entities for financial prediction. On average, the model demonstrates an improvement in accuracy of 40.3% across ten different stock price predictions. These findings are expounded through relevant theories, offering a theoretical foundation for observed patterns and indicating a promising direction for future research in this domain.

This article presents a network embedding approach to automatically generate tags for microblog users. Instead of using text data, we aim to annotate microblog users with meaningful tags by leveraging rich social link data. To utilize directed social links, we use two kinds of node representations for modeling user interest in terms of their followers and followees, respectively. To alleviate the sparsity problem, we propose a novel method based on two transformation functions for capturing implicit interest similarity. Different from previous works on capturing high-order proximity, our model is able to directly characterize the effect of the context user on the proximity of node pairs. Another novelty of our model is that the importance scores of users learned from the classic PageRank algorithm are utilized to set the link weights. By using such weights, our model is more capable of disentangling the interest similarity evidence of a link. We jointly consider the above factors when designing the final objective function. We construct a very large evaluation set consisting of 2.6M users, 0.5M tags, and 0.8B following links. To our knowledge, it is the largest reported dataset for microblog user tagging in the literature. Extensive experiments on this dataset demonstrate the effectiveness of the proposed approach. We implement this approach with several optimization techniques, which makes our model easy to scale to very large social networks. Ubiquitous social links provide important data resources to understand user interests. Our work provides an effective and efficient solution to annotate user interests solely using the link data, which has important practical value in industry. To illustrate the use of our models, we implement a demonstration system for visualizing, navigating, and searching microblog users.

Single source refers to the unified measurement of different aspects of the same individual based on data from multiple sources. In the context of UGC, single source data can be used to study at least two important but as yet insufficiently investigated theoretical issues. First, single source data are ideal sources for studying inter-platform dynamics such as user migration across UGC platforms. Second, single source data can help to link individual self-reported cognitive factors with web crawled individual behavior logs, to achieve better understanding of individual behavior. In this paper, we select a random sample of Sina Blog users and collect their behavior information on both Sina Blog and Sina Weibo platforms; we also conduct an online survey to collect information about their cognitive factors. Merging all data together, we observe and quantify different behavior patterns of the same people across Blog and Weibo; we also identify alternative attractiveness and perceived popularity as significant drivers of one of the most important inter-platform dynamics - switching behavior.

Cooperation and competition (jointly called "coopetition") are two modes of interactions among a set of concurrent topics on social media. How do topics cooperate or compete with each other to gain public attention? Which topics tend to cooperate or compete with one another? Who plays the key role in coopetition-related interactions? We answer these intricate questions by proposing a visual analytics system that facilitates the in-depth analysis of topic coopetition on social media. We model the complex interactions among topics as a combination of carry-over, coopetition recruitment, and coopetition distraction effects. This model provides a close functional approximation of the coopetition process by depicting how different groups of influential users (i.e., "topic leaders") affect coopetition. We also design EvoRiver, a time-based visualization, that allows users to explore coopetition-related interactions and to detect dynamically evolving patterns, as well as their major causes. We test our model and demonstrate the usefulness of our system based on two Twitter data sets (social topics data and business topics data).

How do various topics compete for public attention when they are spreading on social media? What roles do opinion leaders play in the rise and fall of competitiveness of various topics? In this study, we propose an expanded topic competition model to characterize the competition for public attention on multiple topics promoted by various opinion leaders on social media. To allow an intuitive understanding of the estimated measures, we present a timeline visualization through a metaphoric interpretation of the results. The visual design features both topical and social aspects of the information diffusion process by compositing ThemeRiver with storyline style visualization. ThemeRiver shows the increase and decrease of competitiveness of each topic. Opinion leaders are drawn as threads that converge or diverge with regard to their roles in influencing the public agenda change over time. To validate the effectiveness of the visual analysis techniques, we report the insights gained on two collections of Tweets: the 2012 United States presidential election and the Occupy Wall Street movement.

This study explores the factors influencing citations to Internet studies by assessing the relative explanatory power of three perspectives: normative theory, the social constructivist approach, and a natural growth mechanism. Using data on 7,700+ articles of Internet studies published in 100+ Social Sciences Citation Index (SSCI)‐listed journals in 2000–2009, the study adopted a multilevel model to disentangle the impact between article‐ and journal‐level factors on citations. This research strategy resulted in a number of both expected and surprising findings. The primary determinants for citations are found to be journal‐level factors, accounting for 14% of the variances in citations of Internet studies. The impact of some, if not all, article‐level factors on citations are moderated by journal‐level factors. Internet studies, like studies in other areas (e.g., management, demography, and ecology), are cited more for rhetorical purposes, as suggested by the social constructivist approach, rather than as a form of reward, as argued by normative theory. The impact of time on citations varies across journals, which creates a growing “citation gap” for Internet studies published in journals with different characteristics.

As opposed to representing a document as a "bag of words" in most information retrieval applications, we propose a model of representing a web page as sets of named entities of multiple types. Specifically, four types of named entities are extracted, namely person, geographic location, organization, and time. Moreover, the relations among these entities are also extracted, weighted, classified and marked by labels. On top of this model, some interesting applications are demonstrated. In particular, we introduce a notion of person-activity, which contains four different elements: person, location, time and activity. With this notion and based on a reasonably large set of web pages, we are able to show how one person's activities can be attributed by time and location, which gives a good idea of the mobility of the person under question.

In this paper, we describe an experimental search engine on our Chinese web archive since 2001. The original data set contains nearly 3 billion Chinese web pages crawled from past 5 years. From the collection, 430 million "article-like" pages are selected and then partitioned into 68 million sets of similar pages. The titles and publication dates are determined for the pages. An index is built. When searching, the system returns related pages in a chronological order. This way, if a user is interested in news reports or commentaries for certain previously happened event, he/she will be able to find a quite rich set of highly related pages in a convenient way.

The shape of the Web in terms of its graphical structure has been a widely interested topic. Two graphs, Bow Tie and Daisy, have stood out from previous research. In this work, we take a different approach, by viewing the Web as a hierarchy of three levels, namely page level, host level, and domain level. Such structures are analyzed and compared with a snapshot of Chinese Web in early 2006, involving 830 million pages, 17 million hosts, and 0.8 million domains. Some interesting results have emerged. For example, the Chinese Web appears more like a teapot (with a large size of SCC, a medium size of IN and a small size of OUT) at page level than the classic bow tie or daisy shape. Some challenging phenomena are also observed. For example, the INs become much smaller than OUTs at host and domain levels. Future work will tackle these puzzles.