Andrea Fronzetti Colladon

The power of reciprocal knowledge sharing relationships for startup success

Purpose – The purpose of this paper is to examine the innovative capabilities of biotech start-ups in relation to geographic proximity and knowledge sharing interaction in the R & D network of a major high-tech cluster. Design/methodology/approach – This study compares longitudinal informal communication networks of researchers at biotech start-ups with company patent applications in subsequent years. For a year, senior R & D staff members from over 70 biotech firms located in the Boston biotech cluster were polled and communication information about interaction with peers, universities and big pharmaceutical companies was collected, as well as their geolocation tags. Findings – Location influences the amount of communication between firms, but not their innovation success. Rather, what matters is communication intensity and recollection by others. In particular, there is evidence that rotating leadership – changing between a more active and passive communication style – is a predictor of innovative perfo...

Using social network analysis to prevent money laundering

We analyzed over 33,000 financial operations involving an Italian factoring company.We present network construction techniques based on different risk factors.Social network metrics are an important addition to anti-money laundering.Cluster analysis on tacit link networks can help identify suspicious actors.Our models and metrics are easy to replicate and to integrate into existing systems. This research explores the opportunities for the application of network analytic techniques to prevent money laundering. We worked on real world data by analyzing the central database of a factoring company, mainly operating in Italy, over a period of 19 months. This database contained the financial operations linked to the factoring business, together with other useful information about the company clients.We propose a new approach to sort and map relational data and present predictive models - based on network metrics - to assess risk profiles of clients involved in the factoring business. We find that risk profiles can be predicted by using social network metrics. In our dataset, the most dangerous social actors deal with bigger or more frequent financial operations; they are more peripheral in the transactions network; they mediate transactions across different economic sectors and operate in riskier countries or Italian regions. Finally, to spot potential clusters of criminals, we propose a visual analysis of the tacit links existing among different companies who share the same owner or representative. Our findings show the importance of using a network-based approach when looking for suspicious financial operations and potential criminals.

Forecasting managerial turnover through e-mail based social network analysis

In this study we propose a method based on e-mail social network analysis to compare the communication behavior of managers who voluntarily quit their job and managers who decide to stay. Collecting 18 months of e-mail, we analyzed the communication behavior of 866 managers, out of which 111 left a large global service company. We compared differences in communication patterns by computing social network metrics, such as betweenness and closeness centrality, and content analysis indicators, such as emotionality and complexity of the language used. To study the emergence of managers disengagement, we made a distinction based on the period of e-mail data examined. We observed communications during months 5 and 4 before managers left, and found significant variations in both their network structure and use of language. Results indicate that on average managers who quit had lower closeness centrality and less engaged conversations. In addition, managers who chose to quit tended to shift their communication behavior starting from 5 months before leaving, by increasing their degree and closeness centrality, the complexity of their language, as well as their oscillations in betweenness centrality and the number of nudges they need to send to peers before getting an answer. Turnover can be predicted via email-based social network analysis.Collecting 18 months of emails, we analyzed social network metrics for 866 managers.Managers who quit have lower closeness centrality and less engaged conversations.After deciding to leave, managers tend to invert their communication behavior.

It is rotating leaders who build the swarm: social network determinants of growth for healthcare virtual communities of practice

Purpose The purpose of this paper is to identify the factors influencing the growth of healthcare virtual communities of practice (VCoPs) through a seven-year longitudinal study conducted using metrics from social-network and semantic analysis. By studying online communication along the three dimensions of social interactions (connectivity, interactivity and language use), the authors aim to provide VCoP managers with valuable insights to improve the success of their communities. Design/methodology/approach Communications over a period of seven years (April 2008 to April 2015) and between 14,000 members of 16 different healthcare VCoPs coexisting on the same web platform were analysed. Multilevel regression models were used to reveal the main determinants of community growth over time. Independent variables were derived from social network and semantic analysis measures. Findings Results show that structural and content-based variables predict the growth of the community. Progressively, more people will join a community if its structure is more centralised, leaders are more dynamic (they rotate more) and the language used in the posts is less complex. Research limitations/implications The available data set included one Web platform and a limited number of control variables. To consolidate the findings of the present study, the experiment should be replicated on other healthcare VCoPs. Originality/value The study provides useful recommendations for setting up and nurturing the growth of professional communities, considering, at the same time, the interaction patterns among the community members, the dynamic evolution of these interactions and the use of language. New analytical tools are presented, together with the use of innovative interaction metrics, that can significantly influence community growth, such as rotating leadership.

Using four different online media sources to forecast the crude oil price

This study looks for signals of economic awareness on online social media and tests their significance in economic predictions. The study analyses, over a period of 2 years, the relationship between the West Texas Intermediate daily crude oil price and multiple predictors extracted from Twitter; Google Trends; Wikipedia; and the Global Data on Events, Location and Tone (GDELT) database. Semantic analysis is applied to study the sentiment, emotionality and complexity of the language used. Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX) models are used to make predictions and to confirm the value of the study variables. Results show that the combined analysis of the four media platforms carries valuable information in making financial forecasting. Twitter language complexity, GDELT number of articles and Wikipedia page reads have the highest predictive power. This study also allows a comparison of the different fore-sighting abilities of each platform, in terms of how many days ahead a platform can predict a price movement before it happens. In comparison with previous work, more media sources and more dimensions of the interaction and of the language used are combined in a joint analysis.

Quality Management in the Design of TLC Call Centers

Call centres rely heavily on the self-service paradigm through the use of an automated IVR (Interactive Voice Response) system. The service time delivered by the IVR is a major component of the overall QoS (Quality of Service) delivered by the call centre. We analyse the structure and service times of IVR systems through a case study of five call centres in the telecommunications sector. The service trees of the call centres under survey are reconstructed by complete exploration and analysed through a set of metrics. The present design of service trees leads to service times typically larger than those spent waiting for a human agent and to excessively long announcements, with a negative impact on the overall QoS. Imbalances in the popularity of the services offered by the IVR can be exploited to reduce remarkably the average service time, by properly matching the most popular services with the shortest service times.

What Makes You Popular: Beauty, Personality or Intelligence?

This study explores the determinants of popularity within friendship and advice networks. We involved almost 200 college students in an experiment to predict how personality traits, self-monitoring, creativity, intelligence, energy, and beauty influence the development of friendship and advice networks. Our results indicate that physical attractiveness is a key to develop both friendship and task-related interactions, whereas perceived intelligence and creativity play an important role in the advice network. Our findings seem to support the idea that there might be a kernel of truth in the stereotype that attractiveness correlates with positive social traits and successful outcomes.

Measuring the Level of Global Awareness on Social Media

We introduce a novel approach to measure the degree of global awareness by analyzing social media. Tracking six honest signals of collaboration on Twitter (strong leadership, rotating leadership, balanced contribution, responsiveness, honest sentiment, shared language), we illustrate how social media builds collective awareness through Twitter activity while prominent events are unfolding. We compare three events in 2015: Francogeddon—the sudden unpegging of the Swiss Franc to the Euro, the launch of the Apple watch, and the Greek vote on Grexit, finding that Francogeddon shows the highest short-term impact on global awareness.

Assessing perceived organizational leadership styles through twitter text mining

We propose a text classification tool based on support vector machines for the assessment of organizational leadership styles, as appearing to Twitter users. We collected Twitter data over 51 days, related to the first 30 Italian organizations in the 2015 ranking of Forbes Global 2000—out of which we selected the five with the most relevant volumes of tweets. We analyzed the communication of the company leaders, together with the dialogue among the stakeholders of each company, to understand the association with perceived leadership styles and dimensions. To assess leadership profiles, we referred to the 10‐factor model developed by Barchiesi and La Bella in 2007. We maintain the distinctiveness of the approach we propose, as it allows a rapid assessment of the perceived leadership capabilities of an enterprise, as they emerge from its social media interactions. It can also be used to show how companies respond and manage their communication when specific events take place, and to assess their stakeholders reactions.

Big data analysis of economic news: Hints to forecast macroeconomic indicators

We propose a novel method to improve the forecast of macroeconomic indicators based on social network and semantic analysis techniques. In particular, we explore variables extracted from the Global Database of Events, Language, and Tone, which monitors the world’s broadcast, print and web news. We investigate the locations and the countries involved in economic events (such as business or economic agreements), as well as the tone and the Goldstein scale of the news where the events are reported. We connect these elements to build three different social networks and to extract new network metrics, which prove their value in extending the predictive power of models only based on the inclusion of other economic or demographic indices. We find that the number of news, their tone, the network constraint of nations and their betweenness centrality oscillations are important predictors of the Gross Domestic Product per Capita and of the Business and Consumer Confidence indices.