Connecting social media to e-commerce:cold-start product recommendation using microblogging information

In recent years, the boundaries between e-commerce and social networking have become increasingly blurred. Many e-commerce websites support the mechanism of social login where users can sign on the websites using their social network identities such as their Facebook or Twitter accounts. Users can also post their newly purchased products on microblogs with links to the e-commerce product web pages. In this paper, we propose a novel solution for cross-site cold-start product recommendation, which aims to recommend products from e-commerce websites to users at social networking sites in 'cold-start' situations, a problem which has rarely been explored before. A major challenge is how to leverage knowledge extracted from social networking sites for cross-site cold-start product recommendation. We propose to use the linked users across social networking sites and e-commerce websites (users who have social networking accounts and have made purchases on e-commerce websites) as a bridge to map users' social networking features to another feature representation for product recommendation. In specific, we propose learning both users' and products' feature representations (called user embeddings and product embeddings, respectively) from data collected from e-commerce websites using recurrent neural networks and then apply a modified gradient boosting trees method to transform users' social networking features into user embeddings. We then develop a feature-based matrix factorization approach which can leverage the learnt user embeddings for cold-start product recommendation. Experimental results on a large dataset constructed from the largest Chinese microblogging service Sina Weibo and the largest Chinese B2C e-commerce website JingDong have shown the effectiveness of our proposed framework.

Social media in emergency management:Twitter as a tool for communicating risks to the public

One of the main challenges of emergency management lies in communicating risks to the public. On some occasions, risk communicators might seek to increase awareness over emerging risks, while on others the aim might be to avoid escalation of public reactions. Social media accounts offer an opportunity to rapidly distribute critical information and in doing so to mitigate the impact of emergencies by influencing public reactions. This article draws on theories of risk and emergency communication in order to consider the impact of Twitter as a tool for communicating risks to the public. We analyse 10,020 Twitter messages posted by the official accounts of UK local government authorities (councils) in the context of two major emergencies: the heavy snow of December 2010 and the riots of August 2011. Twitter was used in a variety of ways to communicate and manage associated risks including messages to provide official updates, encourage protective behaviour, increase awareness and guide public attention to mitigating actions. We discuss the importance of social media as means of increasing confidence in emergency management institutions.

The New (Marketing) Role of Firms as Media Content Providers – The case of SME’s Strategic Social Media Presence

In the new social media context, it is gradually more common to say that each party can itself be considered a media content provider, firms included (through their brand pages). This tendency is reflected in a rising professional field called “content marketing”. This study incorporates the perspective of small and medium-sized enterprises (SMEs) into the scope of social media (SM) as a marketing communications and media content distribution system. In an exploratory content analysis of 20 official SM brand pages with 1281 analyzed posts the authors study how SMEs respond to the advent of a new paradigm of marketing communications with special attention to their usage of media-specific contents. SM impels companies to eventually rethink the traditional one-way communication flow of their marketing messages and to incorporate a new, two-way communication into their marketing strategy, where (their engaged and involved) users can create, modify, share and discuss content related to the firm’s activity. This study’s preliminary results show that diffusing content generally acts for SMEs as a facilitator to involve fans by offering a thematized space for them to manifest themselves in company-related topics. Therefore, content adds to the firms’ possibilities of brand positioning by offering a reflection of fans’ company- and contentrelated behavior, which is a supplementary source of information.

The Attributes of Social Media as a Strategic Marketing Communication Tool

New digital trends are transforming the media industry landscape, modifying elemental characteristics and attitudes of companies as well as of consumers. Firms often claim that their presence in social media (SM) is a key element to success. SM helps companies rethink the traditional one-way flow of their marketing messages and to incorporate a new interactive pattern into their communications. Nevertheless, these tendencies involve problems of strategic myopia for firms that do not structurally integrate these tools. One main problem is that institutions can rarely differentiate between the various types of SM and the attributes thereof, while the literature equally reveals a number of contradictions in the subject. The present conceptual paper lays the foundations of a strategic approach to SM and discusses its theoretical implications. Following an overview on the concept of SM, through a content analysis of the specialized management literature (n = 14), we present various best practices and reflect on the apparent lack of strategic thinking in using SM as a marketing application. Then, we compare these practical examples with general marketing strategy theory. By merging theory and practice, we aim to provide an insight towards a well-founded application of SM as a genuinely strategic marketing tool.

"Lájk első látásra?" – Mi inspirálja a márkák kedvelését az online térben, kis vendéglátóhelyek esetében? ("Like at first sight?" – What inspires liking brands in online social media in the case of small catering establishments?)

A márkatulajdonosok számára elsődleges fontosságú, hogy feltérképezzék saját márkaközösségüket, ezáltal is elősegítve a közösségi fókuszú kommunikációs tevékenységüket. Különösen igaz ez a jellemzően kis- és középvállalati formában működő vendéglátóhelyek számára, ahol a közösségi média sokszor az egyetlen rendelkezésre álló marketingkommunikációs eszköz. Empirikus kutatásunkban fogyasztói narratívákat (n=151) elemzünk a tartalomelemzés módszertanával. A válaszadókat arra kértük, hogy írjanak kedvenc vendéglátóhelyükkel való kapcsolatukról az online térben. Elemzésünkben arra keressük a választ, hogy a márkaközösségek tagjai milyen belső indíttatásból kerültek kapcsolatba kedvenc vendéglátóhelyeikkel a közösségi platformokon. Az elsősorban fogyasztási élményekhez kötött kapcsolat online közösségi térbe való kiterjesztésére olyan belső motivációkat tártunk fel, mint a pragmatikusabb információközpontú indíttatások (pl. kizárólagos információk, naprakészség, vállalati ajánlatok, közösségimédia-specifikus tartalmakhoz való hozzáférés igénye), az érzelmi kötődés kifejezése (pl. nosztalgia, ismerősöknek való ajánlás, személyes érintettség), a társas befolyás (oldalak kedvelése mint kommunikációs tartalom, konformitás, önkifejezés), valamint a vállalati alapképességeken túlmutató egyéb tematikus kapcsolódások. ____ It is of primary importance for brand owners to map their own brand community, in order to stimulate their social-focused communication activity. This is especially true for typically small and medium-sized catering enterprises, where in most cases, social media is the only available marketing communications tool. In our empirical research, we analyze consumer narratives (n=151) with the methodology of content analysis. We asked the respondents to write about their relationship with their most preferred catering establishments in the online social sphere. In our research, we search for the inner intention by which members of brand communities got connected with their most preferred catering establishments on social platforms. We revealed such inner motivations for users extending a primarily experience (an consumption) based relationship to the online social sphere like rather pragmatic, information-focused intentions (e.g. exclusive information, timeliness, company offers, access claim for social media -specific contents), the expression of emotional binding (e.g. nostalgia, reference for acquaintances, personal involvement), social influence (the like as communication content, conformity, self-expression), and other thematic linkages beyond core company competences.

"Lájkolom őket, de ennék is náluk?" – Aktivitásra buzdító kis- és középvállalati közösségimédia-tevékenységek fogyasztói fogadtatása magyarországi vendéglátóhelyek példáján keresztül ("I like them, but would I eat at their place?" – Encouraging social media activities of small and medium-sized enterprises and their consumerreactions – the case of Hungarian catering establishments)

A vendéglátóipari egységek kommunikációjában fontos szerepe van a közösségi médiában való jelenlétnek. Hazánkban a leggyakrabban használt felület a Facebook, amely sok ilyen vállalkozás esetében kiemelt fontosságú, vagy akár az egyetlen reálisan elérhető marketingkommunikációs felület. Kutatásunkban azt vizsgáljuk, hogy a felhasználók hogyan érzékelik a feléjük továbbított üzleti célú információkat a közösségi felületen, illetve hogy a fogyasztókra milyen mértékű aktivitás jellemző kedvenc vendéglátóipari egységük oldalán. Ennek céljából szubjektív fogyasztói narratívákat (n=151) elemzünk a kvalitatív tartalomelemzés módszertanával. A válaszadókat arra kértük, hogy írjanak kedvenc vendéglátóhelyükkel való kapcsolatukról az online térben. A "belájkolt" vendéglátóipari egységek felületeinek fogyasztók által észlelt aktivitása segítheti a vállalkozásokat abban, hogy alaptevékenységük elemeinek kommunikálásával, vagy akár ettől teljesen eltérő közösségi stratégiát használva pozicionálják márkájukat. A márkák tudatos tartalommenedzselése hozzájárulhat továbbá a felhasználók virtuális térben való hatékonyabb eléréséhez és bevonásához. ____ Presence in social media is an important element in the communication of catering establishments. The most frequently used platform in Hungary – that is extraordinarily important, or even the only reasonably accessible marketing communications platform for many catering companies – is Facebook. In our research, we analyse how users perceive the business-purposed information forwarded to them on the social media platform, and how intensive are the consumers’ activities on their most preferred catering establishment's site. For this purpose we analyse subjective consumer narratives (N=151) with the methodology of qualitative content analysis. We asked the respondents to write about the relationship with their most preferred catering establishment in the online sphere. Perceived activity of the "liked" catering establishment's platform could help enterprises to position themselves by communicating their core activities, or by using a totally different social strategy. Moreover, conscious content management of brands could contribute to reach and to engage users in the virtual sphere more efficiently.

The Impact of Social Media in the Workplace

Today, individuals communicate easier and faster due to accessibility of the Internet. However, when employees are distracted with social media, it can become a concern for organizations. This paper reviews literature concerning social media and its implications at workplaces, and provides recommendations to control it, using Adams’ equity theory (1963).

Using Social Media to Build Your Academic Brand

This professional development session will review recent research on the use of social media by faculty and academic staff. The bulk of the presentation will focus on social media strategies and techniques that attendees can use to develop and build their academic brand. This session will be useful to various audiences including established faculty, new faculty and graduate students.

Text analytics of social media: Sentiment analysis, event detection and summarization

In the last decade, large numbers of social media services have emerged and been widely used in people's daily life as important information sharing and acquisition tools. With a substantial amount of user-contributed text data on social media, it becomes a necessity to develop methods and tools for text analysis for this emerging data, in order to better utilize it to deliver meaningful information to users. ^ Previous work on text analytics in last several decades is mainly focused on traditional types of text like emails, news and academic literatures, and several critical issues to text data on social media have not been well explored: 1) how to detect sentiment from text on social media; 2) how to make use of social media's real-time nature; 3) how to address information overload for flexible information needs. ^ In this dissertation, we focus on these three problems. First, to detect sentiment of text on social media, we propose a non-negative matrix tri-factorization (tri-NMF) based dual active supervision method to minimize human labeling efforts for the new type of data. Second, to make use of social media's real-time nature, we propose approaches to detect events from text streams on social media. Third, to address information overload for flexible information needs, we propose two summarization framework, dominating set based summarization framework and learning-to-rank based summarization framework. The dominating set based summarization framework can be applied for different types of summarization problems, while the learning-to-rank based summarization framework helps utilize the existing training data to guild the new summarization tasks. In addition, we integrate these techneques in an application study of event summarization for sports games as an example of how to better utilize social media data. ^

Text Analytics of Social Media: Sentiment Analysis, Event Detection and Summarization

In the last decade, large numbers of social media services have emerged and been widely used in people's daily life as important information sharing and acquisition tools. With a substantial amount of user-contributed text data on social media, it becomes a necessity to develop methods and tools for text analysis for this emerging data, in order to better utilize it to deliver meaningful information to users. Previous work on text analytics in last several decades is mainly focused on traditional types of text like emails, news and academic literatures, and several critical issues to text data on social media have not been well explored: 1) how to detect sentiment from text on social media; 2) how to make use of social media's real-time nature; 3) how to address information overload for flexible information needs. In this dissertation, we focus on these three problems. First, to detect sentiment of text on social media, we propose a non-negative matrix tri-factorization (tri-NMF) based dual active supervision method to minimize human labeling efforts for the new type of data. Second, to make use of social media's real-time nature, we propose approaches to detect events from text streams on social media. Third, to address information overload for flexible information needs, we propose two summarization framework, dominating set based summarization framework and learning-to-rank based summarization framework. The dominating set based summarization framework can be applied for different types of summarization problems, while the learning-to-rank based summarization framework helps utilize the existing training data to guild the new summarization tasks. In addition, we integrate these techneques in an application study of event summarization for sports games as an example of how to better utilize social media data.

Labeling large scale social media data using budget-driven One-class SVM classification

The social media classification problems draw more and more attention in the past few years. With the rapid development of Internet and the popularity of computers, there is astronomical amount of information in the social network (social media platforms). The datasets are generally large scale and are often corrupted by noise. The presence of noise in training set has strong impact on the performance of supervised learning (classification) techniques. A budget-driven One-class SVM approach is presented in this thesis that is suitable for large scale social media data classification. Our approach is based on an existing online One-class SVM learning algorithm, referred as STOCS (Self-Tuning One-Class SVM) algorithm. To justify our choice, we first analyze the noise-resilient ability of STOCS using synthetic data. The experiments suggest that STOCS is more robust against label noise than several other existing approaches. Next, to handle big data classification problem for social media data, we introduce several budget driven features, which allow the algorithm to be trained within limited time and under limited memory requirement. Besides, the resulting algorithm can be easily adapted to changes in dynamic data with minimal computational cost. Compared with two state-of-the-art approaches, Lib-Linear and kNN, our approach is shown to be competitive with lower requirements of memory and time.

Social media data in research : provenance challenges?

Postprint

You'll Never Ride Alone: The Role of Social Media in Supporting the Bus Passenger Experience

Postprint

Internet Surveillance after Snowden: A Critical Empirical Study of Computer Experts' Attitudes on Commercial and State Surveillance of the Internet and Social Media post-Edward Snowden

Acknowledgement: The research presented in this paper was conducted as part of the EU FP7 research project PACT (http://www.projectpact.eu), grant agreement number 285635.