Pre- and post-launch emotions in new product development: Insights from twitter analytics of three products

The paper showcases the possible application of social media analytics in new product development (NPD). It compares users’ emotions before and after the launch of three new products in the market—a pizza, a car and a smart phone—for possible inputs for NPD. The user-generated content offers an alternative to conventional survey data and is cross-cultural in nature, relatively inexpensive and provides real-time information about user behaviour. A total of 302,632 tweets that mentioned the three new products before and after the launch were collected and analysed. Sentiment analysis of the tweets from two time periods was conducted and compared. The users’ responses to the pre- and post-launch of three products vary. The dissatisfaction with the new products represented by negative emotions aligns with the market performance. In the pre-launch period, trust and joy were more common for pizza, joy was more common for the car, and trust was more common for the phone. In the post-launch period, anger and disgust were more common for pizza, joy and trust were more common for the car, and joy was more common for only one aspect of the phone. Further analysis showed that for the car and the phone, firms need to focus on user attitudes towards product attributes, whereas for pizza, firms should concentrate on physiological changes, i.e., changes in product attributes, service and promotional sides. By using the proposed alternative approach, businesses can obtain real-time feedback about the expectations and experiences of the new products. The NPD process can be adjusted accordingly.     

The influence of personalization on tag query length in social media search

Social content systems contain enormous collections of unstructured user-generated content, annotated by the collaborative effort of regular Internet users. Tag-clouds have become popular interfaces that allow users to query the database of these systems by clicking relevant terms. However, these single click queries are often not expressive enough to effectively retrieve the desired content. Users have to use multiple clicks or type longer queries to satisfy their information need.     

Collaborative filtering with facial expressions for online video recommendation

Online video recommender systems help users find videos suitable for their preferences. However, they have difficulty in identifying dynamic user preferences. In this study, we propose a new recommendation procedure using changes of users’ facial expressions captured every moment. Facial expressions portray the users’ actual emotions about videos. We can utilize them to discover dynamic user preferences. Further, because the proposed procedure does not rely on historical rating or purchase records, it properly addresses the new user problem, that is, the difficulty in recommending products to users whose past rating or purchase records are not available. To validate the recommendation procedure, we conducted experiments with footwear commercial videos. Experiment results show that the proposed procedure outperforms benchmark systems including a random recommendation, an average rating approach, and a typical collaborative filtering approach for recommendation to both new and existing users. From the results, we conclude that facial expressions are a viable element in recommendation.     

Investigating effectiveness and user acceptance of semantic social tagging for knowledge sharing

Social tagging systems enable users to assign arbitrary tags to various digital resources. However, they face vague-meaning problems when users retrieve or present resources with the keyword-based tags. In order to solve these problems, this study takes advantage of Semantic Web technology and the topological characteristics of knowledge maps to develop a system that comprises a semantic tagging mechanism and triple-pattern and visual searching mechanisms. A field experiment was conducted to evaluate the effectiveness and user acceptance of these mechanisms in a knowledge sharing context. The results show that the semantic social tagging system is more effective than a keyword-based system. The visualized knowledge map helps users capture an overview of the knowledge domain, reduce cognitive effort for the search, and obtain more enjoyment. Traditional keyword tagging with a keyword search still has the advantage of ease of use and the users had higher intention to use it. This study also proposes directions for future development of semantic social tagging systems.     

Cluster searching strategies for collaborative recommendation systems

In-memory nearest neighbor computation is a typical collaborative filtering approach for high recommendation accuracy. However, this approach is not scalable given the huge number of customers and items in typical commercial applications. Cluster-based collaborative filtering techniques can be a remedy for the efficiency problem, but they usually provide relatively lower accuracy figures, since they may become over-generalized and produce less-personalized recommendations. Our research explores an individualistic strategy which initially clusters the users and then exploits the members within clusters, but not just the cluster representatives, during the recommendation generation stage. We provide an efficient implementation of this strategy by adapting a specifically tailored cluster-skipping inverted index structure. Experimental results reveal that the individualistic strategy with the cluster-skipping index is a good compromise that yields high accuracy and reasonable scalability figures.     

Relevance-based language modelling for recommender systems

Relevance-Based Language Models, commonly known as Relevance Models, are successful approaches to explicitly introduce the concept of relevance in the statistical Language Modelling framework of Information Retrieval. These models achieve state-of-the-art retrieval performance in the pseudo relevance feedback task. On the other hand, the field of recommender systems is a fertile research area where users are provided with personalised recommendations in several applications. In this paper, we propose an adaptation of the Relevance Modelling framework to effectively suggest recommendations to a user. We also propose a probabilistic clustering technique to perform the neighbour selection process as a way to achieve a better approximation of the set of relevant items in the pseudo relevance feedback process. These techniques, although well known in the Information Retrieval field, have not been applied yet to recommender systems, and, as the empirical evaluation results show, both proposals outperform individually several baseline methods. Furthermore, by combining both approaches even larger effectiveness improvements are achieved.     

Measuring the interestingness of articles in a limited user environment

Search engines, such as Google, assign scores to news articles based on their relevance to a query. However, not all relevant articles for the query may be interesting to a user. For example, if the article is old or yields little new information, the article would be uninteresting. Relevance scores do not take into account what makes an article interesting, which would vary from user to user. Although methods such as collaborative filtering have been shown to be effective in recommendation systems, in a limited user environment, there are not enough users that would make collaborative filtering effective.     

Applying a multi-dimensional hedonic concept of intrinsic motivation on social tagging tools: A theoretical model and empirical validation

Participation in and adding content to social tagging tools is important for these tools to achieve their purpose of classifying and organizing information. Users of social tagging tools are driven to participate and add tags by extrinsic and intrinsic motivation. Extrinsic motivation is dominating research as a main predictor of why users use information systems. Social tagging tools, as a subset of social media tools, are distinguished by their unique social aspect that makes intrinsic motivation a potential driver for users to add tags to content. Intrinsic motivation, when applied to social tagging tools, could entail many shades that represent different users’ motives for using such tools. In this paper, we add a rich concept of intrinsic motivation to include hedonism as a main predictor of users’ behavior on social tagging tools. We empirically validate a previously proposed theoretical model of three dimensional concepts of hedonism with three components describing individuals’ hedonic state when interacting with social tagging tools: explorability, curiosity, and enjoyment. After a robust and thorough data analysis using structured equation modeling, the results confirm our theoretical model and suggest using a richer concept of enjoyment to reflect a hedonic dimension when investigating intrinsic motivation with interactive social media tools. Our validated model could be the spark of new factors that have the potential to influence user acceptance of information systems in general and in social media tools. This research contributes to the development of attitude-behavior theories that could explain users’ acceptance of dynamic web     

Social network data to alleviate cold-start in recommender system: A systematic review

Recommender Systems are currently highly relevant for helping users deal with the information overload they suffer from the large volume of data on the web, and automatically suggest the most appropriate items that meet users needs. However, in cases in which a user is new to Recommender System, the system cannot recommend items that are relevant to her/him because of lack of previous information about the user and/or the user-item rating history that helps to determine the users preferences. This problem is known as cold-start, which remains open because it does not have a final solution. Social networks have been employed as a good source of information to determine users preferences to mitigate the cold-start problem. This paper presents the results of a Systematic Literature Review on Collaborative Filtering-based Recommender System that uses social network data to mitigate the cold-start problem. This Systematic Literature Review compiled the papers published between 2011–2017, to select the most recent studies in the area. Each selected paper was evaluated and classified according to the depth which social networks used to mitigate the cold-start problem. The final results show that there are several publications that use the information of the social networks within the Recommender System; however, few research papers currently use this data to mitigate the cold-start problem.     

The effects of personalization on user continuance in social networking sites

Social networking sites (SNSs) enable user to personalize their contents and functions. This feature has been assumed as causing positive effects on the use of online information services through enhancing user satisfaction. However, unlike other online information services (non-participatory information services), due to the results of personalization in a certain situation, SNS users cannot help using the SNS even though they feel dissatisfaction on using it. SNSs are different from other information services in the sense that they create and sustain their own value based on the number of participating members. In SNSs, personalization, reflected by updates and maintenance of profile pages, results in such participation. This study hypothesizes that personalization influences on the continued use of SNSs through two factors: switching cost (extrinsic factor) and satisfaction (intrinsic factor). Web-based survey was conducted with the samples of 677 SNS users from six universities in the US. In-person interviews were conducted with 25 university students to elicit their thoughts on the SNSs. Quantitative analysis employed by testing the proposed model with five hypotheses through a structural equation modeling (SEM) technique. The transcribed interview data was analyzed following the constant comparative technique. The main findings indicate that, as expected, the personalization increases its switching cost as well as satisfaction, which results in further use of SNSs. These findings suggest that it is necessary to consider both extrinsic and intrinsic factors of user perceptions when adding personalization features on SNSs.     

Predicting semantic preferences in a socio-semantic system with collaborative filtering: A case study

This paper proposes collaborative filtering as a means to predict semantic preferences by combining information on social ties with information on links between actors and semantics. First, the authors present an overview of the most relevant collaborative filtering approaches, showing how they work and how they differ. They then compare three different collaborative filtering algorithms using articles published by New York Times journalists from 2003 to 2005 to predict preferences, where preferences refer to journalists’ inclination to use certain words in their writing. Results show that while preference profile similarities in an actor’s neighbourhood are a good predictor of her semantic preferences, information on her social network adds little to prediction accuracy.     

Combining different evaluation systems on social media for measuring user satisfaction

Web 2.0 allows people to express and share their opinions about products and services they buy/use. These opinions can be expressed in various ways: numbers, texts, emoticons, pictures, videos, audios, and so on. There has been great interest in the strategies for extracting, organising and analysing this kind of information. In a social media mining framework, in particular, the use of textual data has been explored in depth and still represents a challenge. On a rating and review website, user satisfaction can be detected both from a rating scale and from the written text. However, in common practice, there is a lack of algorithms able to combine judgments provided with both comments and scores. In this paper we propose a strategy to jointly measure the user evaluations obtained from the two systems. Text polarity is detected with a sentiment-based approach, and then combined with the associated rating score. The new rating scale has a finer granularity. Moreover, also enables the reviews to be ranked. We show the effectiveness of our proposal by analysing a set of reviews about the Uffizi Gallery in Florence (Italy) published on TripAdvisor.     

Leveraging social influence based on users activity centers for point-of-interest recommendation

Recommender Systems (RSs) aim to model and predict the user preference while interacting with items, such as Points of Interest (POIs). These systems face several challenges, such as data sparsity, limiting their effectiveness. In this paper, we address this problem by incorporating social, geographical, and temporal information into the Matrix Factorization (MF) technique. To this end, we model social influence based on two factors: similarities between users in terms of common check-ins and the friendships between them. We introduce two levels of friendship based on explicit friendship networks and high check-in overlap between users. We base our friendship algorithm on users’ geographical activity centers. The results show that our proposed model outperforms the state-of-the-art on two real-world datasets. More specifically, our ablation study shows that the social model improves the performance of our proposed POI recommendation system by 31% and 14% on the Gowalla and Yelp datasets in terms of Precision@10, respectively.     

Social commerce research: Definition,research themes and the trends

Social commerce, an emerging phenomenon rooted in social media and Web 2.0 technologies, has attracted the attention of many researchers. The number of publications on social commerce has grown exponentially in the past 10 years. Now, social commerce has become a significant emerging research area. In this paper, we first define the boundary of social commerce research and then attempt to review the extant literature in this area comprehensively and systematically. Based on the definition, this study surveyed 1369 peer-reviewed academic publications in the social media, Web 2.0, and other related areas. Following the survey, 418 of the publications were identified as social commerce research. Then, latent semantic analysis (LSA), a text mining approach, was applied to summarize the current state of social commerce research. LSA results show that there are three major research themes in the current social commerce research: organization, advertisement, and word-of-mouth. Each theme discusses topics such as innovation, user-generated content, and reputation, among others. In addition, we identify some interesting trends. The first main trend is that innovation, corporate reputation, and user-generated content remain the major research topics, although they are experiencing a slight decline. The second main trend is that online reviews, trust, and e-word-of-mouth are attracting more attention from researchers.     

A probabilistic music recommender considering user opinions and audio features

A recommender system has an obvious appeal in an environment where the amount of on-line information vastly outstrips any individual’s capability to survey. Music recommendation is considered a popular application area. In order to make personalized recommendations, many collaborative music recommender systems (CMRS) focus on capturing precise similarities among users or items based on user historical ratings. Despite the valuable information from audio features of music itself, however, few studies have investigated how to utilize information extracted directly from music for personalized recommendation in CMRS. In this paper, we describe a CMRS based on our proposed item-based probabilistic model, where items are classified into groups and predictions are made for users considering the Gaussian distribution of user ratings. In addition, this model has been extended for improved recommendation performance by utilizing audio features that help alleviate three well-known problems associated with data sparseness in collaborative recommender systems: user bias, non-association, and cold start problems in capturing accurate similarities among items. Experimental results based on two real-world data sets lead us to believe that content information is crucial in achieving better personalized recommendation beyond user ratings. We further show how primitive audio features can be combined into aggregate features for the proposed CRMS and analyze their influences on recommendation performance. Although this model was developed originally for music collaborative recommendation based on audio features, our experiment with the movie data set demonstrates that it can be applied to other domains.     

Building user profiles based on sequences for content and collaborative filtering

Modeling user profiles is a necessary step for most information filtering systems – such as recommender systems – to provide personalized recommendations. However, most of them work with users or items as vectors, by applying different types of mathematical operations between them and neglecting sequential or content-based information. Hence, in this paper we study how to propose an adaptive mechanism to obtain user sequences using different sources of information, allowing the generation of hybrid recommendations as a seamless, transparent technique from the system viewpoint. As a proof of concept, we develop the Longest Common Subsequence (LCS) algorithm as a similarity metric to compare the user sequences, where, in the process of adapting this algorithm to recommendation, we include different parameters to control the efficiency by reducing the information used in the algorithm (preference filter), to decide when a neighbor is considered useful enough to be included in the process (confidence filter), to identify whether two interactions are equivalent (δ-matching threshold), and to normalize the length of the LCS in a bounded interval (normalization functions). These parameters can be extended to work with any type of sequential algorithm.We evaluate our approach with several state-of-the-art recommendation algorithms using different evaluation metrics measuring the accuracy, diversity, and novelty of the recommendations, and analyze the impact of the proposed parameters. We have found that our approach offers a competitive performance, outperforming content, collaborative, and hybrid baselines, and producing positive results when either content- or rating-based information is exploited.     

A concept–relationship acquisition and inference approach for hierarchical taxonomy construction from tags

Taxonomy construction is a resource-demanding, top–down, and time consuming effort. It does not always cater for the prevailing context of the captured information. This paper proposes a novel approach to automatically convert tags into a hierarchical taxonomy. Folksonomy describes the process by which many users add metadata in the form of keywords or tags to shared content. Using folksonomy as a knowledge source for nominating tags, the proposed method first converts the tags into a hierarchy. This serves to harness a core set of taxonomy terms; the generated hierarchical structure facilitates users’ information navigation behavior and permits personalizations. Newly acquired tags are then progressively integrated into a taxonomy in a largely automated way to complete the taxonomy creation process. Common taxonomy construction techniques are based on 3 main approaches: clustering, lexico-syntactic pattern matching, and automatic acquisition from machine-readable dictionaries. In contrast to these prevailing approaches, this paper proposes a taxonomy construction analysis based on heuristic rules and deep syntactic analysis. The proposed method requires only a relatively small corpus to create a preliminary taxonomy. The approach has been evaluated using an expert-defined taxonomy in the environmental protection domain and encouraging results were yielded.     

Social media analytics – Challenges in topic discovery,data collection,and data preparation

Since an ever-increasing part of the population makes use of social media in their day-to-day lives, social media data is being analysed in many different disciplines. The social media analytics process involves four distinct steps, data discovery, collection, preparation, and analysis. While there is a great deal of literature on the challenges and difficulties involving specific data analysis methods, there hardly exists research on the stages of data discovery, collection, and preparation. To address this gap, we conducted an extended and structured literature analysis through which we identified challenges addressed and solutions proposed. The literature search revealed that the volume of data was most often cited as a challenge by researchers. In contrast, other categories have received less attention. Based on the results of the literature search, we discuss the most important challenges for researchers and present potential solutions. The findings are used to extend an existing framework on social media analytics. The article provides benefits for researchers and practitioners who wish to collect and analyse social media data.